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

    Neuronpedia

    INDEX
    Explanations

    subject

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    堤
    -0.07
    箦
    -0.07
    谒
    -0.07
     Trio
    -0.07
    lsi
    -0.07
     nz
    -0.07
    hế
    -0.07
     foods
    -0.07
    nął
    -0.07
     gods
    -0.07
    POSITIVE LOGITS
    以後
    0.08
     partnered
    0.07
    SPATH
    0.07
     이러
    0.07
    未来发展
    0.07
     snapchat
    0.07
     알아
    0.07
    onChange
    0.06
    有期
    0.06
    _RENDERER
    0.06
    Act Density 0.001%

    No Known Activations