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

    Neuronpedia

    INDEX
    Explanations

    html closing tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ων
    -0.07
    液
    -0.07
    第三
    -0.07
     произ
    -0.06
     прий
    -0.06
    agrams
    -0.06
     区
    -0.06
    _MATERIAL
    -0.06
    .;↵
    -0.06
    vailable
    -0.06
    POSITIVE LOGITS
     observes
    0.06
     smoking
    0.06
    vertis
    0.06
    .ident
    0.06
    .Stage
    0.06
     huyện
    0.06
    research
    0.05
     erkek
    0.05
    =add
    0.05
    (Msg
    0.05
    Act Density 0.058%

    No Known Activations