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

    Neuronpedia

    INDEX
    Explanations

    adjectives describing evaluation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'aj
    -0.08
    义
    -0.08
     sat
    -0.08
    abor
    -0.08
     Identify
    -0.07
    -family
    -0.07
     nghĩa
    -0.07
    home
    -0.07
     identifying
    -0.07
    Sac
    -0.07
    POSITIVE LOGITS
     તમે
    0.08
    Rose
    0.08
     прод
    0.08
    莉
    0.08
    Bindable
    0.08
     coincid
    0.08
     Holly
    0.08
     you'd
    0.08
     substances
    0.08
    /how
    0.08
    Act Density 0.042%

    No Known Activations