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

    Neuronpedia

    INDEX
    Explanations

    placeholder token

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mining
    0.40
    mining
    0.40
    miner
    0.40
     Assist
    0.38
    muj
    0.36
     magic
    0.35
     remain
    0.35
     miner
    0.35
    ka
    0.35
     induction
    0.35
    POSITIVE LOGITS
    faf
    0.43
     TNFR
    0.41
    MNOP
    0.40
    icle
    0.40
    IPE
    0.39
    urare
    0.39
    ffe
    0.39
    HNO
    0.39
     craindre
    0.39
     prenn
    0.38
    Act Density 0.000%

    No Known Activations