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

    Neuronpedia

    INDEX
    Explanations

    ; followed by word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kenapa
    0.43
     बजाय
    0.42
     olio
    0.41
     celu
    0.41
     desafio
    0.41
     delegates
    0.41
     pse
    0.40
     deleg
    0.40
     помо
    0.40
     notify
    0.39
    POSITIVE LOGITS
    strand
    0.37
    꾸
    0.37
    relle
    0.37
     tract
    0.37
    irt
    0.37
    eller
    0.36
    ум
    0.36
    achs
    0.36
    richten
    0.34
     Tract
    0.33
    Act Density 0.000%

    No Known Activations