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

    Neuronpedia

    INDEX
    Explanations

    assignment and initialization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Nike
    0.48
    elun
    0.43
     corporal
    0.41
    Nike
    0.41
    achel
    0.38
     nike
    0.38
    olina
    0.37
    𝙳
    0.36
     Clinics
    0.36
     oxidación
    0.36
    POSITIVE LOGITS
     make
    0.57
    make
    0.53
     reflect
    0.47
    reflect
    0.46
    strings
    0.45
     strings
    0.44
    []
    0.43
     MAKE
    0.42
    append
    0.42
    Make
    0.41
    Act Density 0.008%

    No Known Activations