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

    Neuronpedia

    INDEX
    Explanations

    ip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Se
    -0.07
     maize
    -0.07
     learns
    -0.07
    .BO
    -0.07
     Spawn
    -0.06
     другого
    -0.06
     Simpsons
    -0.06
    awner
    -0.06
     parasite
    -0.06
     yok
    -0.06
    POSITIVE LOGITS
    flo
    0.07
     bedroom
    0.07
    ..
    0.07
    随
    0.07
     Recovery
    0.06
     سبب
    0.06
    配置
    0.06
    -br
    0.06
     Sharon
    0.06
    _QUAL
    0.06
    Act Density 0.005%

    No Known Activations