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

    Neuronpedia

    INDEX
    Explanations

    locked/unlocked/free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cartridge
    -0.08
     jak
    -0.07
     offense
    -0.07
    pickle
    -0.07
     acknow
    -0.07
    🔗
    -0.07
    缸
    -0.06
    Jak
    -0.06
     jersey
    -0.06
     colonization
    -0.06
    POSITIVE LOGITS
    WebResponse
    0.08
    商业
    0.07
    SCRIPT
    0.07
    _mat
    0.07
    Volume
    0.07
    预备
    0.06
    玃
    0.06
     threatening
    0.06
    _SCORE
    0.06
    קטור
    0.06
    Act Density 0.041%

    No Known Activations