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

    Neuronpedia

    INDEX
    Explanations

    clicking to download

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decaying
    0.44
     philipp
    0.44
     sy
    0.42
     fissures
    0.38
    varo
    0.38
    itri
    0.38
     worlds
    0.37
    yp
    0.37
     screw
    0.37
    pack
    0.37
    POSITIVE LOGITS
    ޏ
    0.41
    峦
    0.40
     disponibilidade
    0.39
     исклю
    0.38
     ProductName
    0.38
     asistentes
    0.38
     Supervisor
    0.37
     suburb
    0.37
    の影響
    0.36
     chồng
    0.36
    Act Density 0.000%

    No Known Activations