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

    Neuronpedia

    INDEX
    Explanations

    we

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    足球
    -0.07
     Chat
    -0.07
     Damn
    -0.06
    νώ
    -0.06
     addicts
    -0.06
    _NE
    -0.06
     язы
    -0.06
     spell
    -0.06
     journalist
    -0.06
     Song
    -0.06
    POSITIVE LOGITS
    inus
    0.07
    550
    0.07
    .realm
    0.06
    .NoSuch
    0.06
    _BASIC
    0.06
     Medina
    0.06
    |=↵
    0.06
    вався
    0.06
    ?↵↵↵↵↵↵
    0.06
    ルの
    0.06
    Act Density 0.000%

    No Known Activations