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

    Neuronpedia

    INDEX
    Explanations

    –

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .react
    -0.07
     베스트
    -0.06
     awarded
    -0.06
    .endswith
    -0.06
    _np
    -0.06
     prepare
    -0.06
     ql
    -0.06
    ICO
    -0.06
    _SAVE
    -0.06
    eacher
    -0.06
    POSITIVE LOGITS
     punishable
    0.06
     irc
    0.06
    ']."
    0.06
    _BRANCH
    0.06
    ılan
    0.06
    ngör
    0.06
     invading
    0.06
    dığı
    0.06
     stip
    0.06
    лев
    0.06
    Act Density 0.235%

    No Known Activations