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

    Neuronpedia

    INDEX
    Explanations

    descriptions or sentence fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     usleep
    -0.06
    —are
    -0.06
    ♀
    -0.06
     endings
    -0.06
     Damage
    -0.06
    brities
    -0.06
     Attacks
    -0.06
    �
    -0.06
     HDC
    -0.06
     Fiction
    -0.05
    POSITIVE LOGITS
     illusions
    0.07
    _gb
    0.06
     labour
    0.06
     uni
    0.06
     конферен
    0.06
    encion
    0.06
     PYTHON
    0.06
    ő
    0.06
     '?
    0.06
     certainly
    0.06
    Act Density 0.041%

    No Known Activations