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

    Neuronpedia

    INDEX
    Explanations

    if you provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     funktion
    0.46
     vegetal
    0.44
     ejec
    0.43
     reale
    0.43
     boul
    0.42
     trabajo
    0.41
     viens
    0.41
     enceinte
    0.41
     jetzt
    0.40
     arbete
    0.40
    POSITIVE LOGITS
     बजाय
    0.60
    without
    0.56
    instead
    0.53
     instead
    0.52
     which
    0.52
     সহজে
    0.52
    that
    0.50
     without
    0.50
    which
    0.49
     rather
    0.46
    Act Density 0.001%

    No Known Activations