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

    Neuronpedia

    INDEX
    Explanations

    dashes and underscores

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Primera
    -0.07
     Αυ
    -0.07
    statt
    -0.07
    өн
    -0.07
    شان
    -0.07
     പുറ
    -0.07
    signal
    -0.07
    external
    -0.07
    :Get
    -0.07
     outside
    -0.07
    POSITIVE LOGITS
     endnu
    0.09
     ännu
    0.09
     necesariamente
    0.08
     какая
    0.08
     forgotten
    0.08
    bije
    0.08
     unbedingt
    0.08
     важно
    0.08
     એવો
    0.08
     �
    0.08
    Act Density 0.004%

    No Known Activations