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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    mers
    -0.07
    ВС
    -0.07
     Interpret
    -0.06
     spacer
    -0.06
     grey
    -0.06
     reef
    -0.06
    �
    -0.06
     nervous
    -0.06
     некотор
    -0.06
    roid
    -0.06
    POSITIVE LOGITS
    .performance
    0.07
    .catalog
    0.07
    plural
    0.06
    checkpoint
    0.06
    CTX
    0.06
     fetch
    0.06
    zerbai
    0.06
     Cly
    0.06
     vay
    0.06
    intval
    0.06
    Act Density 0.000%

    No Known Activations