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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     태
    -0.07
    /ex
    -0.07
    .context
    -0.07
     baff
    -0.07
     티
    -0.07
     FOUND
    -0.07
     베
    -0.07
     mayor
    -0.06
    -shaped
    -0.06
     decentralized
    -0.06
    POSITIVE LOGITS
    .TextAlign
    0.07
     (`
    0.06
     �
    0.06
    roups
    0.06
    ::/
    0.06
    рех
    0.06
     cigaret
    0.06
    ~":"
    0.06
    Scores
    0.06
    ří
    0.06
    Act Density 0.047%

    No Known Activations