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

    Neuronpedia

    INDEX
    Explanations

    Ships and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (batch
    -0.07
     тол
    -0.07
     технолог
    -0.06
    131
    -0.06
     Apprentice
    -0.06
    _tar
    -0.06
     exemptions
    -0.06
     hei
    -0.06
     Crit
    -0.06
    Iron
    -0.06
    POSITIVE LOGITS
     slows
    0.07
     sono
    0.06
     calming
    0.06
    bigint
    0.06
     TimeSpan
    0.06
    gaard
    0.06
     FileManager
    0.06
    DECL
    0.06
    upakan
    0.06
    usaha
    0.06
    Act Density 0.025%

    No Known Activations