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

    Neuronpedia

    INDEX
    Explanations

    focuses a suggestion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ollut
    0.54
     elu
    0.49
     idee
    0.47
     nią
    0.46
     değil
    0.45
     není
    0.45
     emis
    0.44
     proposte
    0.44
     ostatnich
    0.44
     është
    0.43
    POSITIVE LOGITS
    ired
    0.42
     एकल
    0.40
    ks
    0.40
    ────────────────
    0.40
     едино
    0.39
    idio
    0.39
    audience
    0.39
    ت
    0.39
    वारी
    0.38
    ने
    0.38
    Act Density 0.002%

    No Known Activations