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

    Neuronpedia

    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fatigue
    -0.07
    αιο
    -0.07
    езда
    -0.07
    乌
    -0.07
    .getHost
    -0.06
    ibold
    -0.06
     diets
    -0.06
     gran
    -0.06
     Pass
    -0.06
    	Request
    -0.06
    POSITIVE LOGITS
    rolley
    0.07
    .translation
    0.06
    printer
    0.06
     inverted
    0.06
    _exact
    0.06
    HONE
    0.06
    救
    0.06
    autical
    0.06
    "){
    0.06
    '){
    0.06
    Act Density 0.005%

    No Known Activations