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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remission
    -0.09
    -containing
    -0.09
    configured
    -0.08
    Configured
    -0.08
    či
    -0.08
    								↵
    -0.08
     situated
    -0.07
     बावजूद
    -0.07
    —but
    -0.07
     (?)
    -0.07
    POSITIVE LOGITS
     honor
    0.07
     hon
    0.07
     Honor
    0.07
    ulang
    0.07
     aceite
    0.07
     honorary
    0.07
     government's
    0.07
    emmin
    0.07
     Lore
    0.07
     группе
    0.07
    Act Density 0.004%

    No Known Activations