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

    Neuronpedia

    INDEX
    Explanations

    derivatives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -instagram
    -0.06
    >
    -0.06
    Immutable
    -0.06
    갤
    -0.06
    _created
    -0.06
     �
    -0.06
    бы
    -0.06
    nave
    -0.06
     heute
    -0.06
    >.↵
    -0.06
    POSITIVE LOGITS
     fiz
    0.06
    Plug
    0.06
     PHYS
    0.06
     krat
    0.06
     offense
    0.06
     Statistical
    0.06
    []{↵
    0.06
     SOC
    0.06
     frac
    0.06
    Acceler
    0.06
    Act Density 0.001%

    No Known Activations