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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     бух
    -0.07
    ้อม
    -0.07
    Nodes
    -0.06
     reassure
    -0.06
    .]
    -0.06
    ｊ
    -0.06
     dostat
    -0.06
    濃
    -0.06
     саме
    -0.06
     brom
    -0.06
    POSITIVE LOGITS
     Threat
    0.07
     smoke
    0.07
    _display
    0.06
    *'
    0.06
    \Route
    0.06
     เป
    0.06
    having
    0.06
    _NETWORK
    0.06
     wings
    0.06
     původ
    0.06
    Act Density 0.085%

    No Known Activations