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

    Neuronpedia

    INDEX
    Explanations

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="../
    -0.08
     _↵↵
    -0.07
    _THE
    -0.07
     chtěl
    -0.07
     причина
    -0.07
    _PLAY
    -0.07
    _APPLICATION
    -0.07
     Everything
    -0.06
    .rename
    -0.06
    	builder
    -0.06
    POSITIVE LOGITS
     alış
    0.06
    �
    0.06
    rol
    0.06
     aliqu
    0.06
    427
    0.06
    erek
    0.06
    tery
    0.06
     şehir
    0.06
    ัฒ
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations