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

    Neuronpedia

    INDEX
    Explanations

    alone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fff
    -0.07
     Crop
    -0.07
     surfing
    -0.07
    Hey
    -0.06
    imler
    -0.06
     Hess
    -0.06
    四
    -0.06
    ferences
    -0.06
     COS
    -0.06
    اهای
    -0.06
    POSITIVE LOGITS
     alone
    0.11
     Alone
    0.09
    ligne
    0.09
    独
    0.08
    负责
    0.07
    ANO
    0.07
    one
    0.07
    le
    0.07
    ↵	
↵
    0.07
    LE
    0.06
    Act Density 0.008%

    No Known Activations