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

    Neuronpedia

    INDEX
    Explanations

    configuration or code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᵘ
    0.41
     runners
    0.38
    [::-
    0.38
    ุท
    0.37
     adverse
    0.36
    +".
    0.35
    uhà
    0.35
    ೭
    0.35
     اعتراض
    0.35
    vvvert
    0.35
    POSITIVE LOGITS
     Evam
    0.43
    ansir
    0.41
     Де
    0.40
     adulta
    0.39
     Cade
    0.39
    ститу
    0.38
     dewasa
    0.38
     young
    0.38
     register
    0.38
     Similarly
    0.38
    Act Density 0.000%

    No Known Activations