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

    Neuronpedia

    INDEX
    Explanations

    ft_ programming functions and spasticity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.89
     —
    0.71
     a
    0.64
    0
    0.63
     agama
    0.61
     menyebabkan
    0.60
     επα
    0.60
     not
    0.60
     e
    0.58
     laki
    0.58
    POSITIVE LOGITS
    ड
    0.71
    рел
    0.67
     Dado
    0.65
    ре
    0.64
     UCL
    0.64
    THE
    0.63
    си
    0.62
    рів
    0.62
    ૧
    0.62
    イ
    0.61
    Act Density 0.002%

    No Known Activations