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

    Neuronpedia

    INDEX
    Explanations

    data analysis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     embraced
    -0.08
    Points
    -0.07
     evaluate
    -0.07
     brows
    -0.07
     easier
    -0.07
     rewards
    -0.07
    理
    -0.07
    texture
    -0.07
    measure
    -0.07
     sharks
    -0.07
    POSITIVE LOGITS
     #%
    0.07
     pictureBox
    0.07
    vailability
    0.07
    مم
    0.06
    _Null
    0.06
    _Address
    0.06
     işi
    0.06
     Phú
    0.06
    	rb
    0.06
     ppl
    0.06
    Act Density 0.026%

    No Known Activations