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

    Neuronpedia

    INDEX
    Explanations

    spatial orientation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    justify
    -0.07
    takes
    -0.06
    党
    -0.06
     вже
    -0.06
    ячи
    -0.06
     Vic
    -0.06
    ……」↵↵
    -0.06
    ka
    -0.06
    лях
    -0.06
    icast
    -0.06
    POSITIVE LOGITS
    _SCORE
    0.07
     liv
    0.07
     homosexuality
    0.07
     Wonderland
    0.07
     emitting
    0.06
     getOrder
    0.06
     Emerging
    0.06
     Procedure
    0.06
     person
    0.06
    _OLD
    0.06
    Act Density 0.039%

    No Known Activations