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

    Neuronpedia

    INDEX
    Explanations

    gradle implementation and runtime dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    androidx
    0.38
    🎣
    0.37
    鎖
    0.37
    lt
    0.36
     ég
    0.36
    ικο
    0.36
     trajectory
    0.35
     適
    0.35
    Autowired
    0.35
    cultural
    0.35
    POSITIVE LOGITS
    쌉
    0.40
    angal
    0.36
     Inge
    0.36
    െന്നും
    0.35
     liệt
    0.35
     syllables
    0.35
     logger
    0.34
    批评
    0.34
    感觉
    0.34
    Lily
    0.34
    Act Density 0.000%

    No Known Activations