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

    Neuronpedia

    INDEX
    Explanations

    Kerr

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (no
    -0.07
    يات
    -0.07
    اص
    -0.07
    517
    -0.06
    ------------------------------
    -0.06
    Mono
    -0.06
     None
    -0.06
    radio
    -0.06
    ança
    -0.06
    .WRAP
    -0.06
    POSITIVE LOGITS
     milk
    0.07
     Designer
    0.06
     Derby
    0.06
     disable
    0.06
     Eng
    0.06
     addresses
    0.06
    challenge
    0.06
     cycl
    0.06
     Dancing
    0.06
     Customer
    0.06
    Act Density 0.000%

    No Known Activations