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

    Neuronpedia

    INDEX
    Explanations

    criteria

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     restraining
    -0.06
    }')↵↵
    -0.06
    Jump
    -0.06
     Poss
    -0.06
     McCabe
    -0.06
    bservice
    -0.06
     pottery
    -0.06
     alleging
    -0.06
    toBeInTheDocument
    -0.06
     Died
    -0.05
    POSITIVE LOGITS
     vr
    0.07
    rates
    0.07
    High
    0.07
     ford
    0.06
    .frames
    0.06
    ，上
    0.06
     airplane
    0.06
     "),
    0.06
    ère
    0.06
    high
    0.06
    Act Density 0.040%

    No Known Activations