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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _For
    -0.07
     Eld
    -0.07
    -for
    -0.07
     for
    -0.07
    .Any
    -0.06
     Phen
    -0.06
    ifikace
    -0.06
    —for
    -0.06
     ETF
    -0.06
     Clemson
    -0.06
    POSITIVE LOGITS
     explained
    0.06
    Const
    0.06
     connexion
    0.06
    拥
    0.06
    _TOKEN
    0.06
    737
    0.06
     transactions
    0.06
    ‘s
    0.06
    Abstract
    0.06
     pledge
    0.06
    Act Density 0.072%

    No Known Activations