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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oyun
    -0.07
     autoload
    -0.06
    -done
    -0.06
    _decoder
    -0.06
     sanctuary
    -0.06
     kuzey
    -0.06
    erspective
    -0.06
     lines
    -0.06
    tea
    -0.06
    iště
    -0.06
    POSITIVE LOGITS
    แบบ
    0.07
    Assets
    0.07
     Micro
    0.07
     dead
    0.06
     overturned
    0.06
    �
    0.06
     posing
    0.06
    ♀♀♀♀
    0.06
    超
    0.06
     grandfather
    0.06
    Act Density 0.007%

    No Known Activations