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

    Neuronpedia

    INDEX
    Explanations

    relu

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ACP
    -0.08
    arseille
    -0.07
    /XML
    -0.07
    	id
    -0.07
     globe
    -0.07
    onden
    -0.07
     dataSnapshot
    -0.07
     God
    -0.07
    xdd
    -0.07
     organizations
    -0.07
    POSITIVE LOGITS
     avoided
    0.07
    "]){↵
    0.07
     Deze
    0.07
    _GR
    0.07
    _ELEM
    0.07
     stacking
    0.06
     rewriting
    0.06
    ']}↵
    0.06
     дома
    0.06
    (Q
    0.06
    Act Density 0.001%

    No Known Activations