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

    Neuronpedia

    INDEX
    Explanations

    integ

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mari
    -0.08
     Mari
    -0.07
    .pen
    -0.07
    ラ
    -0.07
    ylon
    -0.06
     Baron
    -0.06
     consumo
    -0.06
     cesty
    -0.06
    ALA
    -0.06
     Nar
    -0.06
    POSITIVE LOGITS
    <DateTime
    0.07
     }
↵
↵
↵
    0.06
    वत
    0.06
    Applied
    0.06
     Thinking
    0.06
     threatened
    0.06
     newest
    0.06
     enrolled
    0.06
     That
    0.06
    ounces
    0.06
    Act Density 0.003%

    No Known Activations