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

    Neuronpedia

    INDEX
    Explanations

    Small components of larger things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iam
    -0.07
    datos
    -0.07
    ience
    -0.07
    location
    -0.07
     inaugural
    -0.07
    adies
    -0.07
     Can't
    -0.07
    reiz
    -0.07
     DIR
    -0.06
    first
    -0.06
    POSITIVE LOGITS
    排列
    0.16
     individuais
    0.15
     individuales
    0.15
     individuele
    0.15
     individual
    0.14
     individually
    0.14
     Individual
    0.14
     individuelles
    0.13
    Individual
    0.13
     individuel
    0.13
    Act Density 0.164%

    No Known Activations