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

    Neuronpedia

    INDEX
    Explanations

    data equivalents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     roślin
    0.44
    ポスト
    0.43
     pianta
    0.42
     neuer
    0.41
     poesía
    0.41
     religieux
    0.41
     símbolo
    0.40
     réseaux
    0.39
     veines
    0.39
     laisse
    0.38
    POSITIVE LOGITS
     See
    0.34
     Pret
    0.33
    žky
    0.33
    i
    0.33
    hib
    0.33
    alya
    0.33
    onclick
    0.33
     /**
    0.32
    lid
    0.32
    treating
    0.32
    Act Density 0.000%

    No Known Activations