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

    Neuronpedia

    INDEX
    Explanations

    Names and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IAN
    -1.59
    inian
    -1.45
    ian
    -1.36
    sian
    -1.23
    onian
    -1.20
    lian
    -1.14
    rian
    -1.13
    ianum
    -1.13
    ARIAN
    -1.07
    ilian
    -1.06
    POSITIVE LOGITS
    ism
    0.84
    ne
    0.82
    na
    0.82
    ni
    0.71
    em
    0.70
    ny
    0.69
    ness
    0.63
    ns
    0.62
    es
    0.62
    nu
    0.61
    Act Density 0.033%

    No Known Activations