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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Tree
    -0.07
    afür
    -0.07
    aos
    -0.06
    ILI
    -0.06
     خاص
    -0.06
    jec
    -0.06
    adb
    -0.06
    mot
    -0.06
    igest
    -0.06
    _CB
    -0.06
    POSITIVE LOGITS
     when
    0.11
     When
    0.08
    Lastly
    0.07
    When
    0.07
     surprisingly
    0.07
    	when
    0.07
    when
    0.06
    isActive
    0.06
     Quando
    0.06
    /head
    0.06
    Act Density 0.040%

    No Known Activations