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

    Neuronpedia

    INDEX
    Explanations

    influence official action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கட்டமை
    0.46
     букмекерлик
    0.44
     leftWheel
    0.44
     emocionante
    0.43
     акку
    0.43
     strutture
    0.43
    键盘
    0.42
     başlad
    0.42
     castom
    0.42
     estruturas
    0.42
    POSITIVE LOGITS
     withheld
    0.70
     withhold
    0.65
     withholding
    0.62
     leverage
    0.50
     pressure
    0.47
    actions
    0.47
     investigating
    0.47
     actions
    0.47
     investigations
    0.46
     politic
    0.44
    Act Density 0.004%

    No Known Activations