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

    Neuronpedia

    INDEX
    Explanations

    math operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    йтесь
    -0.08
    �
    -0.08
     neben
    -0.07
    auważ
    -0.07
     functor
    -0.07
    라이
    -0.07
     backdrop
    -0.07
     alarm
    -0.07
     slapped
    -0.07
    (criteria
    -0.07
    POSITIVE LOGITS
     المشاركة
    0.07
    欺诈
    0.07
    迫
    0.07
    戚
    0.07
     inverse
    0.07
    _REPEAT
    0.07
     homeschool
    0.07
    שר
    0.07
     Zurich
    0.07
     skins
    0.07
    Act Density 0.000%

    No Known Activations