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

    Neuronpedia

    INDEX
    Explanations

    numbers and measurements

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ACES
    0.42
     hina
    0.37
    னைய
    0.36
     jett
    0.36
    졀
    0.36
    ínio
    0.35
     tartar
    0.35
    тири
    0.35
     th
    0.34
    URCH
    0.34
    POSITIVE LOGITS
    占
    0.40
    Sl
    0.39
    🌓
    0.39
    lo
    0.37
    ,]
    0.35
    asmuch
    0.35
     glen
    0.35
     ]:
    0.35
    labs
    0.35
     ]
    0.35
    Act Density 0.000%

    No Known Activations