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

    Neuronpedia

    INDEX
    Explanations

    you want or you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obscene
    0.29
     dilation
    0.29
     excre
    0.28
     (
    0.27
     dispersal
    0.27
     wasteful
    0.27
     demarcation
    0.26
     looping
    0.26
     obscures
    0.26
     icy
    0.26
    POSITIVE LOGITS
     pouvez
    0.32
     хотите
    0.31
    want
    0.31
     want
    0.29
     получите
    0.29
     can
    0.29
    accordo
    0.28
     have
    0.27
     yourself
    0.26
    Want
    0.26
    Act Density 0.971%

    No Known Activations