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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Time
    -0.07
    -share
    -0.07
     Serving
    -0.07
    ♀♀
    -0.07
     delivers
    -0.07
    CLOCKS
    -0.07
    'RE
    -0.06
    ?",
    -0.06
    “My
    -0.06
     Me
    -0.06
    POSITIVE LOGITS
     použí
    0.07
    ndern
    0.07
    ripsi
    0.06
    .removeClass
    0.06
    (retval
    0.06
    elopment
    0.06
    _GP
    0.06
     диаг
    0.06
     crist
    0.06
     harder
    0.06
    Act Density 0.055%

    No Known Activations