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

    Neuronpedia

    INDEX
    Explanations

    melting, softening

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Invocation
    -0.07
    His
    -0.07
    	damage
    -0.06
     Dmit
    -0.06
    urdu
    -0.06
    іту
    -0.05
    ，他
    -0.05
    Justice
    -0.05
     تاریخی
    -0.05
     cidade
    -0.05
    POSITIVE LOGITS
     Registers
    0.07
     sums
    0.07
     racked
    0.07
     emotional
    0.07
     gratuites
    0.07
     predictive
    0.06
    loub
    0.06
    ogue
    0.06
    .IsNull
    0.06
     सक
    0.06
    Act Density 0.014%

    No Known Activations