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

    Neuronpedia

    INDEX
    Explanations

    machine learning/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medically
    -0.08
    .amazonaws
    -0.07
     oferece
    -0.07
     statewide
    -0.07
     opa
    -0.07
    -sided
    -0.07
    iders
    -0.07
    _MENU
    -0.07
     staffed
    -0.07
     wire
    -0.07
    POSITIVE LOGITS
    જબ
    0.09
    म्म
    0.09
    appings
    0.09
    ുംബൈ
    0.09
     Theory
    0.08
    osaic
    0.08
    Theory
    0.08
    atrices
    0.08
     tonnes
    0.08
     Theorie
    0.08
    Act Density 0.045%

    No Known Activations