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

    Neuronpedia

    INDEX
    Explanations

    instruction descriptions and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ᚗ
    0.42
     자유
    0.40
     bootstrap
    0.39
    ⨯
    0.39
     Biblia
    0.39
    agangan
    0.38
     BOA
    0.38
    োহণ
    0.37
     Output
    0.37
    වාස
    0.37
    POSITIVE LOGITS
     швидко
    0.38
     pensare
    0.38
     inmediato
    0.38
    नीर
    0.37
    ສະ
    0.36
    किशोर
    0.35
    edit
    0.35
     интел
    0.35
     টি
    0.35
     Mental
    0.34
    Act Density 0.000%

    No Known Activations