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

    Neuronpedia

    INDEX
    Explanations

    permission and study

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    hled
    0.51
    hunger
    0.49
    minLength
    0.48
    rib
    0.48
    nym
    0.47
    approved
    0.46
    lowercase
    0.46
    gares
    0.45
    uvat
    0.45
    gran
    0.45
    POSITIVE LOGITS
    कान
    0.54
    <0x96>
    0.47
     Safety
    0.47
    ิตร
    0.46
    ด้อ
    0.46
     Warnings
    0.44
     SAFETY
    0.44
     Vendors
    0.44
     HTMLSc
    0.43
    ◣
    0.43
    Act Density 0.000%

    No Known Activations