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

    Neuronpedia

    INDEX
    Explanations

    ref

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fierc
    -0.08
     Bauer
    -0.07
     obsc
    -0.07
    σταν
    -0.07
    terní
    -0.07
    "N
    -0.07
    #ga
    -0.06
    골
    -0.06
    'C
    -0.06
    ysi
    -0.06
    POSITIVE LOGITS
    refs
    0.07
     disruption
    0.07
     params
    0.06
    _Ref
    0.06
    REP
    0.06
     श
    0.06
     emailing
    0.06
    (ins
    0.06
    recht
    0.06
    _TypeInfo
    0.06
    Act Density 0.006%

    No Known Activations