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

    Neuronpedia

    INDEX
    Explanations

    loading transformers AutoModelFromPretrained

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     காற்றின்
    0.45
     ISSN
    0.43
    酸素
    0.43
     minima
    0.41
     acumul
    0.41
     oxygen
    0.39
     oxígeno
    0.39
     leuke
    0.39
     という
    0.39
    이라는
    0.38
    POSITIVE LOGITS
    Vt
    0.42
    modelLogin
    0.42
     TRUST
    0.41
    trust
    0.40
    ATYPE
    0.39
    idefinite
    0.39
     trust
    0.38
    dtype
    0.38
    Vk
    0.38
    大事
    0.38
    Act Density 0.019%

    No Known Activations