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

    Neuronpedia

    INDEX
    Explanations

    requiring rollback or requested outside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ꮵ
    0.52
    Ⲁ
    0.52
     Removing
    0.49
    ﮈ
    0.49
    шивания
    0.48
    ས་
    0.48
    >]</
    0.47
    ᓄ
    0.47
    鎳
    0.47
    ᒎ
    0.47
    POSITIVE LOGITS
     huid
    0.47
     unlock
    0.46
     hiv
    0.45
     delect
    0.45
     angel
    0.43
     malice
    0.43
     liquef
    0.42
     embody
    0.41
     proprie
    0.41
     juan
    0.41
    Act Density 0.000%

    No Known Activations