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

    Neuronpedia

    INDEX
    Explanations

    time or quantity

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     husk
    0.38
    الغ
    0.38
     niewiel
    0.37
     inward
    0.36
     ít
    0.36
    𝒜
    0.36
    弱い
    0.35
    சனம்
    0.35
    少
    0.35
    avelmente
    0.35
    POSITIVE LOGITS
     couple
    0.39
    oven
    0.39
     Resolution
    0.38
     pe
    0.37
    half
    0.37
     recovered
    0.37
     half
    0.37
     Couple
    0.36
    otive
    0.36
     loke
    0.36
    Act Density 0.000%

    No Known Activations