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

    Neuronpedia

    INDEX
    Explanations

    human feedback, learn, solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UNESCO
    0.42
     Ment
    0.40
    ÇA
    0.40
    Цена
    0.38
    Cute
    0.37
     À
    0.36
     Desde
    0.36
     mornings
    0.36
     আলোকিত
    0.36
     Honestly
    0.36
    POSITIVE LOGITS
    leun
    0.46
     who
    0.43
    criminal
    0.43
     toxicology
    0.43
     crimes
    0.42
    Blo
    0.42
     criminals
    0.42
     problems
    0.41
     criminal
    0.40
    licts
    0.40
    Act Density 0.000%

    No Known Activations