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

    Neuronpedia

    INDEX
    Explanations

    create your own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     personally
    0.83
     selves
    0.83
     self
    0.81
     Self
    0.80
    self
    0.78
     SELF
    0.74
    Self
    0.73
     Selbst
    0.73
    inschaft
    0.71
     selbst
    0.71
    POSITIVE LOGITS
     its
    1.46
     своя
    1.31
     его
    1.29
    Its
    1.23
     Its
    1.23
     його
    1.21
    its
    1.18
     sua
    1.17
     свои
    1.17
     súa
    1.10
    Act Density 0.202%

    No Known Activations