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

    Neuronpedia

    INDEX
    Explanations

    training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    K
    -0.07
    izer
    -0.07
     refs
    -0.06
    imizer
    -0.06
    853
    -0.06
    ocomplete
    -0.06
    内部
    -0.06
    esor
    -0.06
    ителем
    -0.06
     Matthew
    -0.06
    POSITIVE LOGITS
     thỏa
    0.07
    ogl
    0.07
     Baum
    0.07
     brainstorm
    0.07
    urally
    0.07
     tranqu
    0.06
    $GLOBALS
    0.06
    �
    0.06
     tư
    0.06
     smartphone
    0.06
    Act Density 0.013%

    No Known Activations