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

    Neuronpedia

    INDEX
    Explanations

    Inability/difficulty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     archaeology
    -0.07
    riot
    -0.07
    istica
    -0.07
    angers
    -0.07
     astronomy
    -0.07
    ्श
    -0.07
    STACK
    -0.07
     подраз
    -0.07
    -0.07
     Jes
    -0.07
    POSITIVE LOGITS
     stubborn
    0.08
     conceptual
    0.08
     שום
    0.07
    provided
    0.07
     elusive
    0.07
     sequer
    0.07
    되지
    0.07
     হয়
    0.07
    \Routing
    0.07
     Atr
    0.07
    Act Density 0.052%
    No Known Activations