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

    Neuronpedia

    INDEX
    Explanations

    Oct

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owering
    -0.07
    _vec
    -0.07
    .loading
    -0.06
    aking
    -0.06
     menus
    -0.06
     creek
    -0.06
     chase
    -0.06
    rin
    -0.06
     últ
    -0.06
     edge
    -0.06
    POSITIVE LOGITS
     госп
    0.07
     CString
    0.06
    Зап
    0.06
    (Self
    0.06
     アイ
    0.06
    γων
    0.06
     floatValue
    0.06
     Self
    0.06
    .Relative
    0.06
     招
    0.06
    Act Density 0.004%

    No Known Activations