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

    Neuronpedia

    INDEX
    Explanations

    how to instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     proportionally
    0.82
     suddenly
    0.79
     proportionately
    0.77
     quickly
    0.75
     बदलकर
    0.73
    ானி
    0.71
     shortly
    0.70
     împ
    0.70
     concurrently
    0.69
     ability
    0.69
    POSITIVE LOGITS
    declare
    0.71
     roc
    0.70
    T
    0.67
    τον
    0.66
    return
    0.64
    raccoon
    0.64
    अपना
    0.64
     prüfen
    0.63
     मैनु
    0.63
    CIF
    0.62
    Act Density 0.056%

    No Known Activations