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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     linewidth
    -0.07
    olu
    -0.06
    าเล
    -0.06
     hrs
    -0.06
    cia
    -0.06
    ｊ
    -0.06
    gba
    -0.06
     Warwick
    -0.06
     Ко
    -0.06
    rego
    -0.06
    POSITIVE LOGITS
     physical
    0.07
     halten
    0.07
    Fact
    0.07
    _COMPONENT
    0.07
    .Players
    0.06
    Policy
    0.06
     firsthand
    0.06
    window
    0.06
    invisible
    0.06
    USERNAME
    0.06
    Act Density 0.004%

    No Known Activations