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

    Neuronpedia

    INDEX
    Explanations

    adget

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atter
    -0.07
    ком
    -0.07
     defends
    -0.06
    iac
    -0.06
     immense
    -0.06
    كت
    -0.06
    خم
    -0.06
    ien
    -0.06
    섯
    -0.06
    unque
    -0.06
    POSITIVE LOGITS
     משפטי
    0.08
     Implicit
    0.08
     MsgBox
    0.08
     collaborations
    0.07
     salari
    0.07
     subclasses
    0.07
    Subview
    0.07
     נוסף
    0.07
    Hope
    0.07
     Winners
    0.07
    Act Density 0.381%

    No Known Activations