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

    Neuronpedia

    INDEX
    Explanations

    technical terms followed by specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ogl
    0.52
     Dialog
    0.52
    ရာ
    0.50
     filmes
    0.49
    ̣n
    0.48
     Fraud
    0.47
     brahman
    0.47
    asang
    0.47
     справо
    0.46
     kys
    0.46
    POSITIVE LOGITS
    -
    0.50
    RIC
    0.45
    L
    0.44
    ING
    0.44
    Discard
    0.43
    ዕ
    0.43
    AL
    0.43
    If
    0.43
    pt
    0.42
    Ov
    0.42
    Act Density 0.001%

    No Known Activations