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

    Neuronpedia

    INDEX
    Explanations

    something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sign
    -0.08
    凘
    -0.07
     yayın
    -0.07
     yytype
    -0.07
    izedName
    -0.07
    Blueprint
    -0.07
    睃
    -0.07
    ORIES
    -0.06
     contentValues
    -0.06
    :both
    -0.06
    POSITIVE LOGITS
    𝑓
    0.07
    ₫
    0.07
    _slots
    0.07
    红酒
    0.07
     wins
    0.07
     wrought
    0.06
    cro
    0.06
    .....
    0.06
    notes
    0.06
     ;-)
    0.06
    Act Density 0.030%

    No Known Activations