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

    Neuronpedia

    INDEX
    Explanations

    Health and symptoms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     branch
    -0.07
    probe
    -0.07
    .Run
    -0.07
    iton
    -0.07
     tra
    -0.07
    all
    -0.07
    镭
    -0.06
     nett
    -0.06
     הר
    -0.06
    下半年
    -0.06
    POSITIVE LOGITS
     Ваш
    0.07
    	swap
    0.07
     __________________↵↵
    0.07
    .days
    0.07
     capacità
    0.07
     absorption
    0.06
     SMTP
    0.06
    Ease
    0.06
     enthusiastic
    0.06
    AAP
    0.06
    Act Density 0.007%

    No Known Activations