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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _result
    -0.07
     assistance
    -0.07
    CAC
    -0.07
    _relations
    -0.06
    -bs
    -0.06
     manpower
    -0.06
    ่าท
    -0.06
    paralleled
    -0.06
     forsk
    -0.06
    _PK
    -0.06
    POSITIVE LOGITS
     Brighton
    0.07
     ου
    0.07
     лей
    0.07
     talked
    0.07
    uba
    0.06
     відбу
    0.06
     bows
    0.06
     ego
    0.06
     occurs
    0.06
     authority
    0.06
    Act Density 0.007%

    No Known Activations