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

    Neuronpedia

    INDEX
    Explanations

    fulfill requests, technical explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Tangent
    0.41
    TTL
    0.40
    利益
    0.39
     berasal
    0.38
     ;(
    0.38
     STATIC
    0.38
     underage
    0.37
    ுத
    0.36
    TargetPath
    0.36
     fett
    0.36
    POSITIVE LOGITS
     Bury
    0.40
    rooms
    0.40
     Hang
    0.39
    테
    0.39
    abies
    0.38
    te
    0.38
     quarter
    0.38
     aura
    0.38
     tav
    0.38
    收
    0.38
    Act Density 0.000%

    No Known Activations