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

    Neuronpedia

    INDEX
    Explanations

    described

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tuning
    -0.07
    ptype
    -0.07
     measures
    -0.07
    higher
    -0.07
    álo
    -0.06
     murder
    -0.06
     Moo
    -0.06
    -results
    -0.06
    verity
    -0.06
    .metrics
    -0.06
    POSITIVE LOGITS
     कह
    0.07
     هنگ
    0.07
     сказав
    0.07
    .BLL
    0.06
     Seit
    0.06
     Gow
    0.06
    .ImageField
    0.06
    .Observer
    0.06
    »↵↵
    0.06
    _sw
    0.06
    Act Density 0.007%

    No Known Activations