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

    Neuronpedia

    INDEX
    Explanations

    dangerous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Full
    -0.07
    ite
    -0.07
     STAR
    -0.07
     Star
    -0.06
    etty
    -0.06
    	free
    -0.06
     feet
    -0.06
    Content
    -0.06
     Shader
    -0.06
    Form
    -0.06
    POSITIVE LOGITS
     ActivityCompat
    0.08
    이지
    0.08
     nhiên
    0.07
     husbands
    0.07
     dangerous
    0.07
    uckland
    0.07
    ี.
    0.07
    활동
    0.07
     discovers
    0.07
    .Tables
    0.07
    Act Density 0.011%

    No Known Activations