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

    Neuronpedia

    INDEX
    Explanations

    anatomical position

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    يريا
    0.46
    枷
    0.40
     maggio
    0.40
    敌人
    0.40
    saver
    0.38
    रि
    0.38
     जलन
    0.38
     enemigo
    0.37
    рити
    0.37
    졌다
    0.37
    POSITIVE LOGITS
     whom
    0.58
    whom
    0.51
     grey
    0.44
     Grayson
    0.42
     online
    0.41
     gray
    0.39
     dry
    0.38
     GRAY
    0.38
    комо
    0.37
    clide
    0.37
    Act Density 0.000%

    No Known Activations