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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    War
    -0.07
     war
    -0.07
    998
    -0.07
    署
    -0.07
     Bed
    -0.07
    job
    -0.07
     job
    -0.06
    ('../../../
    -0.06
    opathic
    -0.06
    root
    -0.06
    POSITIVE LOGITS
    _BUSY
    0.07
     scé
    0.07
    альный
    0.07
    thern
    0.06
    clc
    0.06
     hepatitis
    0.06
    (loss
    0.06
     militant
    0.06
    кул
    0.06
     troop
    0.06
    Act Density 0.023%

    No Known Activations