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

    Neuronpedia

    INDEX
    Explanations

    website code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Estados
    -0.07
    Clients
    -0.06
    Alamat
    -0.06
    _dispatch
    -0.06
    keyword
    -0.06
     convo
    -0.06
    filtro
    -0.06
    unken
    -0.06
    .languages
    -0.06
    urers
    -0.06
    POSITIVE LOGITS
     注意
    0.07
     sacr
    0.06
     disregard
    0.06
    یدن
    0.06
    destruct
    0.06
     socially
    0.06
    icus
    0.06
     YELLOW
    0.06
    _IDLE
    0.06
     Advisor
    0.06
    Act Density 0.028%

    No Known Activations