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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ANT
    -0.07
     bruises
    -0.07
    规划
    -0.06
    HSV
    -0.06
    _hard
    -0.06
     یعنی
    -0.06
    118
    -0.06
    _courses
    -0.06
    -buffer
    -0.06
    ecast
    -0.06
    POSITIVE LOGITS
     atop
    0.09
    aptured
    0.07
    κρα
    0.07
    riba
    0.07
    (recipe
    0.07
    opped
    0.07
    uge
    0.07
    cil
    0.06
     üzerine
    0.06
    .minecraft
    0.06
    Act Density 0.009%

    No Known Activations