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

    Neuronpedia

    INDEX
    Explanations

    +

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ces
    -0.07
     Lola
    -0.07
    द
    -0.07
    �
    -0.06
    Assignable
    -0.06
    bab
    -0.06
     злоч
    -0.06
    bero
    -0.06
    sh
    -0.06
     Sto
    -0.06
    POSITIVE LOGITS
    /gr
    0.07
     newList
    0.06
    (V
    0.06
    .sup
    0.06
     Very
    0.06
    ากร
    0.06
     bacon
    0.06
     discourse
    0.06
     experience
    0.06
    :+
    0.06
    Act Density 0.026%

    No Known Activations