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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hostages
    -0.07
    baum
    -0.07
     Far
    -0.07
     Bed
    -0.07
    ratio
    -0.07
     BOARD
    -0.06
    .ids
    -0.06
    _fid
    -0.06
     magnitude
    -0.06
     KN
    -0.06
    POSITIVE LOGITS
     visually
    0.06
    υμ
    0.06
    、どう
    0.06
     pute
    0.06
     boz
    0.06
    	method
    0.05
    .isNull
    0.05
    sell
    0.05
     dalších
    0.05
    หม
    0.05
    Act Density 0.001%

    No Known Activations