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

    Neuronpedia

    INDEX
    Explanations

    variable or testing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getString
    1.38
    aging
    1.36
    𝗹
    1.34
     Gesture
    1.29
    ategy
    1.23
     đẩy
    1.23
     PartialEq
    1.23
    𝘆
    1.22
     Özel
    1.21
     Morph
    1.20
    POSITIVE LOGITS
     partly
    1.36
    یاں
    1.34
    ش
    1.30
    etto
    1.21
     सूची
    1.10
     prohibit
    1.08
    既
    1.07
     حين
    1.07
    ∂
    1.06
    by
    1.05
    Act Density 0.000%

    No Known Activations