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

    Neuronpedia

    INDEX
    Explanations

    suggested

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Depends
    -0.06
     appreciated
    -0.06
     возможность
    -0.06
    //----------------------------------------------------------------------------↵
    -0.06
    -thumb
    -0.06
    주는
    -0.06
    小说
    -0.06
    木
    -0.06
     },
↵
    -0.06
    ～
    -0.06
    POSITIVE LOGITS
     Сим
    0.07
    弋
    0.07
     Vak
    0.06
     imageName
    0.06
     snag
    0.06
    uros
    0.06
     bladder
    0.06
    Popular
    0.06
     typealias
    0.06
    Constants
    0.06
    Act Density 0.000%

    No Known Activations