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

    Neuronpedia

    INDEX
    Explanations

    longevity claims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MyRegisterClass
    0.43
    리즈
    0.43
     végétation
    0.43
    庾
    0.42
    ylar
    0.41
    阝
    0.41
    邓
    0.40
     মুহাম্ম
    0.38
     ezingu
    0.38
    GreaterThan
    0.38
    POSITIVE LOGITS
     wiped
    0.42
     asked
    0.40
     devastated
    0.38
     hard
    0.38
     center
    0.37
    sley
    0.37
     hurried
    0.37
     словами
    0.37
     forced
    0.37
     cheered
    0.36
    Act Density 0.000%

    No Known Activations