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

    Neuronpedia

    INDEX
    Explanations

    contrasting statements and good outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    estrut
    0.55
    viä
    0.54
    íamos
    0.52
    iki
    0.51
    stice
    0.51
    ici
    0.49
    ula
    0.48
    ichi
    0.47
    ją
    0.46
    istra
    0.46
    POSITIVE LOGITS
     torque
    0.54
     animation
    0.52
     acceleration
    0.51
     web
    0.49
     flown
    0.47
     electrons
    0.46
     adver
    0.46
     program
    0.45
     atan
    0.44
     fn
    0.44
    Act Density 0.024%

    No Known Activations