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

    Neuronpedia

    INDEX
    Explanations

    generate content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    torque
    0.44
    code
    0.44
    trash
    0.44
    tilt
    0.43
    Bon
    0.43
    to
    0.43
    fun
    0.43
    Scan
    0.43
    stress
    0.43
    Gran
    0.42
    POSITIVE LOGITS
    a
    0.52
    บอก
    0.44
     አል
    0.44
     대한
    0.43
    كيد
    0.43
     कनेक्शन
    0.42
     aprend
    0.42
     connecter
    0.42
    assertInstanceOf
    0.42
    ್
    0.42
    Act Density 0.001%

    No Known Activations