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

    Neuronpedia

    INDEX
    Explanations

    mane

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Symbols
    -0.07
    っても
    -0.07
     }}>
    -0.07
     Вас
    -0.07
    ós
    -0.07
     слаб
    -0.06
    -hide
    -0.06
     вимог
    -0.06
     المغ
    -0.06
    除了
    -0.06
    POSITIVE LOGITS
     mane
    0.10
     Mane
    0.08
     MAN
    0.07
     Medic
    0.07
     marijuana
    0.07
     entren
    0.07
     denominator
    0.07
     manipulate
    0.07
     concaten
    0.06
     man
    0.06
    Act Density 0.003%

    No Known Activations