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

    Neuronpedia

    INDEX
    Explanations

    Madrid es, screen size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     JUnit
    0.60
     UnitTest
    0.45
     junit
    0.44
     hooking
    0.41
    JUnit
    0.41
     јед
    0.40
    unit
    0.39
    Jed
    0.38
     hooked
    0.38
     Busch
    0.38
    POSITIVE LOGITS
     !)
    0.41
     декора
    0.40
    ˏ
    0.40
     decorate
    0.39
     Τ
    0.38
     Tiere
    0.38
     τὸ
    0.38
    犬
    0.38
    acjach
    0.37
     Т
    0.37
    Act Density 0.000%

    No Known Activations