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

    Neuronpedia

    INDEX
    Explanations

    healthy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    }↵↵↵↵↵
    -0.07
     дот
    -0.07
    Shadow
    -0.07
    .NoError
    -0.06
     Làm
    -0.06
    }↵↵
    -0.06
     مذ
    -0.06
    anova
    -0.06
     confusion
    -0.06
    \Has
    -0.06
    POSITIVE LOGITS
     upt
    0.07
     healthy
    0.06
     trusted
    0.06
     villains
    0.06
    .ap
    0.06
    ung
    0.06
    $xml
    0.06
    yssey
    0.06
    [word
    0.05
     Trusted
    0.05
    Act Density 0.009%

    No Known Activations