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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'I
    -0.07
    'T
    -0.07
    "]]
    -0.07
    .accept
    -0.07
    $con
    -0.06
     Buildings
    -0.06
     dieses
    -0.06
    Volume
    -0.06
     Kann
    -0.06
    Coffee
    -0.06
    POSITIVE LOGITS
     designed
    0.07
     كس
    0.06
    	it
    0.06
     mism
    0.06
    CPP
    0.06
    _REMOVE
    0.06
     Turns
    0.06
    _AURA
    0.06
    religious
    0.06
    辞
    0.06
    Act Density 0.007%

    No Known Activations