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

    Neuronpedia

    INDEX
    Explanations

    tousled hair and names

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocar
    0.43
    oc
    0.38
    ̣c
    0.38
    oce
    0.37
    ory
    0.37
    itosan
    0.37
    kien
    0.37
     उजागर
    0.37
    ยี
    0.36
     oc
    0.35
    POSITIVE LOGITS
    ♠
    0.37
     elects
    0.35
    setPrototypeOf
    0.35
     résultat
    0.34
    メーター
    0.34
     electing
    0.34
     propelled
    0.33
    剎
    0.33
     اخ
    0.33
    フレ
    0.33
    Act Density 0.000%

    No Known Activations