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

    Neuronpedia

    INDEX
    Explanations

    helpful instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fashion
    -0.07
     constellation
    -0.07
    factory
    -0.07
    ▍▍▍▍
    -0.07
    -fashion
    -0.07
    (cur
    -0.06
    [assembly
    -0.06
    requires
    -0.06
     Fashion
    -0.06
     счет
    -0.06
    POSITIVE LOGITS
     Expansion
    0.06
     McG
    0.06
    [self
    0.06
    _end
    0.06
    �프
    0.06
    _password
    0.05
     oct
    0.05
     пром
    0.05
    rot
    0.05
    HQ
    0.05
    Act Density 0.132%

    No Known Activations