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

    Neuronpedia

    INDEX
    Explanations

    determinism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    陴
    0.42
     HUD
    0.39
     apice
    0.38
     अधिसूचना
    0.38
     pelang
    0.36
    曠
    0.36
     kork
    0.36
    赧
    0.35
    крыть
    0.35
     alertas
    0.35
    POSITIVE LOGITS
     deterministic
    2.25
     determin
    2.05
    Deterministic
    2.00
    deterministic
    1.86
     Determin
    1.85
    Determin
    1.56
    determin
    1.42
     determ
    1.22
     reproducibility
    1.19
     DETERMIN
    1.19
    Act Density 0.040%

    No Known Activations