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

    Neuronpedia

    INDEX
    Explanations

    fort and fight urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ouvrard
    0.39
    чений
    0.38
     rivets
    0.36
     heterod
    0.36
    ExternalTaskPojo
    0.36
    ┕
    0.35
     pity
    0.35
     discriminator
    0.34
     concret
    0.34
     Gunn
    0.34
    POSITIVE LOGITS
    Fort
    0.61
     Fort
    0.60
     FORT
    0.55
     Re
    0.52
    Re
    0.50
    FORT
    0.45
    Sens
    0.44
    ઓએ
    0.41
    fort
    0.40
     ре
    0.39
    Act Density 0.029%

    No Known Activations