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

    Neuronpedia

    INDEX
    Explanations

    acids

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     foll
    -0.07
     Front
    -0.07
     CENTER
    -0.06
    PLAN
    -0.06
     rejoice
    -0.06
    xEA
    -0.06
     continuity
    -0.06
    位置
    -0.06
    那
    -0.06
     Temple
    -0.06
    POSITIVE LOGITS
     gioc
    0.07
    Howard
    0.07
    igail
    0.07
     tensor
    0.07
    uiltin
    0.07
     Jorge
    0.07
    -hidden
    0.07
    startswith
    0.07
     Rodgers
    0.06
     Howard
    0.06
    Act Density 0.005%

    No Known Activations