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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CU
    -0.07
    جر
    -0.07
    cu
    -0.06
     simulated
    -0.06
     tek
    -0.06
    मर
    -0.06
    _member
    -0.06
    ιώ
    -0.06
     já
    -0.06
    {'
    -0.06
    POSITIVE LOGITS
    Anywhere
    0.07
     аж
    0.06
    .spaceBetween
    0.06
    _ability
    0.06
    .sparse
    0.06
    igsaw
    0.06
     invalidated
    0.06
     DISABLE
    0.06
    Unload
    0.06
     několika
    0.06
    Act Density 0.004%

    No Known Activations