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

    Neuronpedia

    INDEX
    Explanations

    math expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slots
    -0.06
    tom
    -0.06
     �
    -0.06
     river
    -0.06
    �
    -0.06
    RULE
    -0.06
     UUID
    -0.06
    と
    -0.06
    �
    -0.06
    爆
    -0.06
    POSITIVE LOGITS
    .code
    0.07
    roph
    0.07
    populate
    0.07
     الآن
    0.06
     physically
    0.06
     wirklich
    0.06
    ifying
    0.06
    .Symbol
    0.06
    ient
    0.06
     halinde
    0.06
    Act Density 0.005%

    No Known Activations