Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases associated with love and emotions in relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    First word of a title or quotation

    np_acts-logits-general · gemini-2.0-flash

    syntax error

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    -0.63
     geworden
    -0.51
     pushing
    -0.50
     cojín
    -0.47
     remercie
    -0.47
     tornillo
    -0.45
     how
    -0.43
     pushed
    -0.43
     ioutil
    -0.43
     go
    -0.42
    POSITIVE LOGITS
    TypedDataSet
    0.92
     betweenstory
    0.82
    SharedDtor
    0.79
    IntoConstraints
    0.79
     Italijanski
    0.75
    yntaxException
    0.72
     متعلقه
    0.72
    0.70
    CodeAttribute
    0.70
     <>",
    0.70
    Act Density 0.149%

    No Known Activations