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

    Neuronpedia

    INDEX
    Explanations

    About

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _hd
    -0.07
     Bad
    -0.07
     (+
    -0.07
     ignoring
    -0.07
    ρευ
    -0.07
     Dillon
    -0.06
     Nexus
    -0.06
     ignored
    -0.06
    (rp
    -0.06
    _probability
    -0.06
    POSITIVE LOGITS
    About
    0.10
     About
    0.09
    irection
    0.07
     Ethiopian
    0.06
     alm
    0.06
    >About
    0.06
     ABOUT
    0.06
    (indexPath
    0.06
    =get
    0.06
    i�
    0.06
    Act Density 0.005%

    No Known Activations