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

    Neuronpedia

    INDEX
    Explanations

    have

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    枚
    -0.07
     Kelley
    -0.07
    .Dropout
    -0.07
     Mana
    -0.07
    (ca
    -0.07
    您
    -0.06
     حقوق
    -0.06
    _progress
    -0.06
    	layout
    -0.06
    _ZONE
    -0.06
    POSITIVE LOGITS
     {{$
    0.06
    .fromCharCode
    0.06
    ovaná
    0.06
    -loving
    0.06
    longrightarrow
    0.06
    ヴ
    0.06
     dolphins
    0.06
    üst
    0.06
    given
    0.06
    !</
    0.06
    Act Density 0.078%

    No Known Activations