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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sunrise
    -0.08
     True
    -0.07
    水库
    -0.07
    ke
    -0.07
     одной
    -0.07
    .common
    -0.07
    ater
    -0.07
     Gulf
    -0.07
    VR
    -0.07
     converged
    -0.07
    POSITIVE LOGITS
     maxWidth
    0.07
     comentarios
    0.07
     hüküm
    0.07
    -cut
    0.07
    -points
    0.07
    -hearted
    0.07
     zobow
    0.07
    ：%
    0.07
    领袖
    0.06
    _ctxt
    0.06
    Act Density 0.001%

    No Known Activations