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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mor
    -0.08
    Cor
    -0.07
    ?↵↵↵
    -0.07
     lacked
    -0.07
    ']↵↵↵
    -0.07
    след
    -0.07
    ⼆
    -0.07
    三大
    -0.07
     Wass
    -0.06
     mos
    -0.06
    POSITIVE LOGITS
    .met
    0.07
    🙃
    0.07
     thankful
    0.07
    に関
    0.07
    .Type
    0.07
    /layouts
    0.07
    _MATRIX
    0.07
     {:?}",
    0.07
    .PictureBox
    0.06
    taş
    0.06
    Act Density 0.005%

    No Known Activations