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

    Neuronpedia

    INDEX
    Explanations

    ско, ску, slow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    idunt
    0.38
    odem
    0.38
     Restoration
    0.38
    iber
    0.36
    unities
    0.36
    finity
    0.36
     procesos
    0.35
     disciplina
    0.35
    syst
    0.35
    ipy
    0.35
    POSITIVE LOGITS
     correction
    0.41
     reversal
    0.40
     corrected
    0.39
     correcting
    0.38
    correction
    0.36
     promoter
    0.35
     ne
    0.35
     energ
    0.35
    Brig
    0.35
    Adding
    0.35
    Act Density 0.001%

    No Known Activations