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

    Neuronpedia

    INDEX
    Explanations

    how to administer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    us
    0.54
    eg
    0.53
     r
    0.50
    v
    0.50
    if
    0.50
     df
    0.49
    R
    0.49
    r
    0.49
    0
    0.48
    ec
    0.48
    POSITIVE LOGITS
     Ambassadors
    0.48
    namefont
    0.48
     murió
    0.48
    놁
    0.47
    ኙ
    0.45
    வின்
    0.44
    Managers
    0.44
     Managers
    0.43
    ថ្ង
    0.42
    Descripción
    0.42
    Act Density 0.000%

    No Known Activations