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

    Neuronpedia

    INDEX
    Explanations

    amended/ended

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Live
    -0.07
    rovers
    -0.07
    .dds
    -0.07
    Bright
    -0.07
    Newton
    -0.07
     inset
    -0.07
    quito
    -0.07
    lua
    -0.06
     bt
    -0.06
     Rivera
    -0.06
    POSITIVE LOGITS
    שיטת
    0.07
     acclaim
    0.07
    💟
    0.07
    ycop
    0.07
    기술
    0.07
    InstantiationException
    0.07
     listBox
    0.07
     antigen
    0.07
    טענות
    0.07
     `}↵
    0.07
    Act Density 0.003%

    No Known Activations