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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'nda
    -0.07
    izzazione
    -0.07
     François
    -0.06
     FW
    -0.06
    เกล
    -0.06
    .textView
    -0.06
    _pod
    -0.06
    络
    -0.06
    ovie
    -0.06
    纳
    -0.06
    POSITIVE LOGITS
     ATM
    0.07
     buiten
    0.06
     clang
    0.06
    ottom
    0.06
     bun
    0.06
    @Json
    0.06
    legs
    0.06
    thes
    0.06
     atm
    0.06
    extract
    0.06
    Act Density 0.005%

    No Known Activations