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

    Neuronpedia

    INDEX
    Explanations

    video game or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Той
    1.00
    verhalten
    0.99
    dato
    0.99
    rative
    0.97
    k
    0.97
    ยก
    0.96
     impr
    0.95
    سون
    0.94
    ty
    0.94
    te
    0.93
    POSITIVE LOGITS
     conferencing
    1.55
     clips
    1.48
     clip
    1.47
    jší
    1.35
    📹
    1.31
     footage
    1.30
     nasty
    1.29
    ء
    1.25
     Confer
    1.22
    कॉन
    1.19
    Act Density 0.022%

    No Known Activations