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

    Neuronpedia

    INDEX
    Explanations

    making contributions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iados
    0.45
    ਿ
    0.42
    Deterministic
    0.42
    чними
    0.41
     Noronha
    0.40
    Include
    0.39
    獃
    0.39
    hm
    0.39
    Implementing
    0.39
    ẖ
    0.39
    POSITIVE LOGITS
     alfabeto
    0.50
     Probleme
    0.46
     Cuisine
    0.45
     ruso
    0.45
     Podcast
    0.44
     amino
    0.44
     sexism
    0.43
     porówn
    0.43
     cuisine
    0.43
     podcast
    0.43
    Act Density 0.002%

    No Known Activations