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

    Neuronpedia

    INDEX
    Explanations

    archical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ("[
    -0.07
     hood
    -0.07
    .xy
    -0.07
     nota
    -0.06
    ulan
    -0.06
     prow
    -0.06
    -d
    -0.06
    ],[
    -0.06
    ckt
    -0.06
    407
    -0.06
    POSITIVE LOGITS
     hierarchical
    0.10
     гір
    0.07
    urable
    0.07
     callable
    0.07
     Herrera
    0.07
     Argentina
    0.06
    Resolver
    0.06
    HR
    0.06
     Zambia
    0.06
     HR
    0.06
    Act Density 0.002%

    No Known Activations