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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ovich
    -0.07
    력을
    -0.07
    Context
    -0.07
    ρέπει
    -0.07
     своїм
    -0.07
     contest
    -0.07
     uống
    -0.07
    units
    -0.07
    fony
    -0.07
    lop
    -0.07
    POSITIVE LOGITS
    √
    0.07
     vỏ
    0.06
     setter
    0.06
     startActivityForResult
    0.06
    :test
    0.06
     Kick
    0.06
    /thumb
    0.06
    -speaking
    0.06
     ancestral
    0.06
     respondsToSelector
    0.06
    Act Density 0.021%

    No Known Activations