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

    Neuronpedia

    INDEX
    Explanations

    act Initiatives, ott School, ble AI, ive Lung

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \
    0.42
    <
    0.40
    ai
    0.40
    able
    0.39
    k
    0.38
    se
    0.37
    i
    0.37
    ak
    0.37
    v
    0.37
    脑
    0.37
    POSITIVE LOGITS
    ฯ
    0.45
     एखा
    0.42
     jų
    0.40
     của
    0.39
     jejich
    0.39
     kanilang
    0.37
     vinculado
    0.36
     వారి
    0.36
    RELATIVA
    0.34
     వారికి
    0.34
    Act Density 0.350%

    No Known Activations