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

    Neuronpedia

    INDEX
    Explanations

    linking libraries or linker errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (
    0.71
     Le
    0.67
    楂
    0.65
     Compre
    0.63
    Ле
    0.62
     Data
    0.60
    1
    0.60
     Bracket
    0.59
     S
    0.59
     THAT
    0.58
    POSITIVE LOGITS
     художник
    0.59
     occured
    0.55
    ینک
    0.55
     ordinairement
    0.55
    selfobj
    0.54
    ینی
    0.54
    )=-
    0.52
    অভ
    0.52
    OZ
    0.51
    رځ
    0.51
    Act Density 0.005%

    No Known Activations