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

    Neuronpedia

    INDEX
    Explanations

    -in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erial
    -0.07
    _existing
    -0.07
     beliefs
    -0.06
    resultSet
    -0.06
     LaTeX
    -0.06
     gay
    -0.06
    룹
    -0.06
    .foo
    -0.06
    CONFIG
    -0.06
    érc
    -0.06
    POSITIVE LOGITS
    ималь
    0.06
    ицин
    0.06
    挂
    0.06
     dilation
    0.06
     detach
    0.06
     Req
    0.06
     그래서
    0.06
    Distinct
    0.06
     Edu
    0.06
    =this
    0.06
    Act Density 0.001%

    No Known Activations