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

    Neuronpedia

    INDEX
    Explanations

    allow to handle features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    HCR
    0.38
    サイト
    0.38
    Hfn
    0.37
     לד
    0.37
     sitios
    0.37
    Gd
    0.37
    नियों
    0.36
     intensified
    0.36
     ಮತ್ತ
    0.35
    ndo
    0.35
    POSITIVE LOGITS
     exposition
    0.45
     UC
    0.43
    acyjnych
    0.39
     Tyler
    0.39
     Trent
    0.39
     Wass
    0.39
     recher
    0.38
    UC
    0.38
     paramètres
    0.38
     trellis
    0.37
    Act Density 0.000%

    No Known Activations