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

    Neuronpedia

    INDEX
    Explanations

    wrist strap, Palm Grip, Error Handling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    瀬
    0.42
     ourselves
    0.42
     bankrupt
    0.41
     nuestros
    0.41
     peligros
    0.41
     sales
    0.40
    මාණ
    0.39
     danger
    0.39
    чили
    0.38
    imètres
    0.38
    POSITIVE LOGITS
    integral
    0.41
     integral
    0.40
     Prototype
    0.39
    矮
    0.37
    ienie
    0.36
     integra
    0.36
     Turnpike
    0.36
     Integral
    0.36
     Tans
    0.36
     NTFS
    0.36
    Act Density 0.000%

    No Known Activations