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

    Neuronpedia

    INDEX
    Explanations

    how to do things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     worlds
    -0.07
     resonance
    -0.06
     protagonists
    -0.06
    никами
    -0.06
     guarante
    -0.06
    ीप
    -0.06
    	ip
    -0.06
     borrow
    -0.06
     mejor
    -0.06
     reson
    -0.06
    POSITIVE LOGITS
     obl
    0.07
     sessuali
    0.07
    _USERNAME
    0.07
    setDisplay
    0.06
    opleft
    0.06
     قي
    0.06
     composer
    0.06
     Operand
    0.06
    \ActiveForm
    0.06
    .PostMapping
    0.06
    Act Density 0.004%

    No Known Activations