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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     અગ
    -0.08
    ,F
    -0.08
    _par
    -0.07
     fearing
    -0.07
    ######
    -0.07
     Staat
    -0.07
     radically
    -0.07
    ()+
    -0.07
     →
    -0.07
    ,+
    -0.07
    POSITIVE LOGITS
     uko
    0.07
    "display
    0.07
     Kron
    0.07
     affich
    0.07
    .amazonaws
    0.07
    halts
    0.07
     phrase
    0.07
     Haft
    0.07
    �
    0.07
    亂
    0.07
    Act Density 0.041%

    No Known Activations