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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -pack
    -0.08
    _expect
    -0.06
     причин
    -0.06
    圈
    -0.06
     Anything
    -0.06
    mue
    -0.06
    rigesimal
    -0.06
    脚
    -0.06
     �
    -0.06
    (front
    -0.06
    POSITIVE LOGITS
     OMG
    0.08
     تاریخ
    0.07
     managing
    0.06
     Biblical
    0.06
     piş
    0.06
    digital
    0.06
     Ibn
    0.06
     alleges
    0.06
     Invitation
    0.06
     hairstyle
    0.06
    Act Density 0.002%

    No Known Activations