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

    Neuronpedia

    INDEX
    Explanations

    ##

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dsl
    -0.09
    'ezie
    -0.09
    war
    -0.08
     हूं
    -0.08
    óch
    -0.08
    违法吗
    -0.08
     nube
    -0.08
    Welkom
    -0.08
     politica
    -0.07
     الصغيرة
    -0.07
    POSITIVE LOGITS
    Overall
    0.12
     insgesamt
    0.11
     Overall
    0.11
     overall
    0.11
     overarching
    0.10
     combining
    0.10
     Combined
    0.10
    Combined
    0.10
     Insgesamt
    0.10
     Gesam
    0.09
    Act Density 0.036%

    No Known Activations