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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classroom
    -0.07
     textual
    -0.07
    ég
    -0.07
    Calibri
    -0.07
     OMAP
    -0.07
     stepping
    -0.06
     cycle
    -0.06
     strained
    -0.06
     Pur
    -0.06
     lr
    -0.06
    POSITIVE LOGITS
     noun
    0.07
    �
    0.06
     قدر
    0.06
    ://'
    0.06
    .Save
    0.06
    ::$
    0.06
    _jet
    0.06
    LECT
    0.06
     randomness
    0.06
    stringLiteral
    0.06
    Act Density 0.011%

    No Known Activations