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

    Neuronpedia

    INDEX
    Explanations

    questions/instructions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sang
    -0.07
     Race
    -0.06
    ]+
    -0.06
     Invest
    -0.06
     ®
    -0.06
    ')[
    -0.06
     outsider
    -0.06
    ®
    -0.06
    ]{
    -0.06
    .album
    -0.06
    POSITIVE LOGITS
    Chr
    0.07
    cxx
    0.07
    _calendar
    0.07
    柱
    0.06
    继续
    0.06
     ελλην
    0.06
    何か
    0.06
    LDAP
    0.06
    stab
    0.06
    pellier
    0.06
    Act Density 0.011%

    No Known Activations