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

    Neuronpedia

    INDEX
    Explanations

    abuse and addiction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ስታ
    0.49
    ウム
    0.47
    unat
    0.46
    がございます
    0.45
    blur
    0.44
    гал
    0.44
    hyst
    0.44
    लैंड
    0.43
    too
    0.43
    šanu
    0.43
    POSITIVE LOGITS
     arousal
    0.52
     a
    0.51
     l
    0.50
     Com
    0.48
     CB
    0.47
    a
    0.47
     C
    0.46
     Iter
    0.46
     Erect
    0.46
     Comb
    0.46
    Act Density 0.004%

    No Known Activations