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

    Neuronpedia

    INDEX
    Explanations

    motivational topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    annonce
    -0.07
     sp
    -0.06
     usr
    -0.06
     sc
    -0.06
    .JButton
    -0.06
    leftrightarrow
    -0.06
    ummings
    -0.06
    ="--
    -0.06
    \xff
    -0.06
     polic
    -0.06
    POSITIVE LOGITS
     Treasure
    0.08
    сия
    0.07
     profits
    0.07
    Plug
    0.07
     Nature
    0.06
     nemůže
    0.06
     Країна
    0.06
     bestellen
    0.06
    �
    0.06
    _OBJ
    0.06
    Act Density 0.193%

    No Known Activations