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

    Neuronpedia

    INDEX
    Explanations

    集

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =password
    -0.08
     acqua
    -0.08
    .crypto
    -0.08
     fread
    -0.08
     производство
    -0.08
     compressor
    -0.08
     prison
    -0.08
     пароль
    -0.08
     crud
    -0.08
     prototypes
    -0.08
    POSITIVE LOGITS
     enrichment
    0.10
    richment
    0.10
    (gca
    0.09
    筛
    0.09
    _analysis
    0.08
    _auc
    0.08
    ída
    0.08
     বিষয়
    0.08
     જી
    0.08
    _top
    0.08
    Act Density 0.002%

    No Known Activations