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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CAL
    -0.07
    �
    -0.07
    plit
    -0.06
     tangent
    -0.06
    itives
    -0.06
    otel
    -0.06
    ��
    -0.06
     diese
    -0.06
    iversary
    -0.06
     frail
    -0.06
    POSITIVE LOGITS
    86
    0.08
    sson
    0.07
    论
    0.07
     gén
    0.07
     핵
    0.07
     sok
    0.07
     document
    0.07
     Obama
    0.07
    Extension
    0.07
    kon
    0.07
    Act Density 0.050%

    No Known Activations