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

    Neuronpedia

    INDEX
    Explanations

    spatial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ξε
    -0.07
    xbc
    -0.06
     franchises
    -0.06
     mattress
    -0.06
     KP
    -0.06
    优势
    -0.06
    เฮ
    -0.06
     staring
    -0.06
    _MARKER
    -0.06
    652
    -0.06
    POSITIVE LOGITS
     spatial
    0.15
     Spatial
    0.12
    .spatial
    0.10
    Spatial
    0.09
    atial
    0.08
    patial
    0.08
    殺
    0.07
     Built
    0.07
    Built
    0.07
     raids
    0.06
    Act Density 0.003%

    No Known Activations