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

    Neuronpedia

    INDEX
    Explanations

    am

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     revisit
    -0.07
     самый
    -0.06
    טיס
    -0.06
    April
    -0.06
     ogó
    -0.06
    -dark
    -0.06
    入选
    -0.06
     oversh
    -0.06
    完成
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    ◖
    0.07
    ustainable
    0.07
     handleMessage
    0.07
     expressing
    0.07
    .removeClass
    0.07
     girlfriend
    0.07
    .getExternal
    0.07
    react
    0.07
     Threads
    0.07
    Regular
    0.07
    Act Density 0.001%

    No Known Activations