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

    Neuronpedia

    INDEX
    Explanations

    enablement

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ┴
    -0.07
    цев
    -0.07
     şiş
    -0.06
    放在
    -0.06
     gelecek
    -0.06
    饭
    -0.06
     verbosity
    -0.06
    щин
    -0.06
    temps
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    BMW
    0.07
     Analy
    0.06
    .RESULT
    0.06
     Plays
    0.06
    Yahoo
    0.06
     will
    0.06
    ))↵↵↵
    0.06
    лав
    0.06
    iostream
    0.06
     Compensation
    0.06
    Act Density 0.127%

    No Known Activations