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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alto
    -0.07
     다음과
    -0.07
    沟
    -0.06
    Conditions
    -0.06
     Clamp
    -0.06
    콩
    -0.06
    _SUFFIX
    -0.06
     Columbus
    -0.06
     خور
    -0.06
     serotonin
    -0.06
    POSITIVE LOGITS
     pe
    0.07
     CCT
    0.07
    역시
    0.06
     Pe
    0.06
     KeyValue
    0.06
    laz
    0.06
    	t
    0.06
    Phys
    0.06
     vect
    0.06
     Hannah
    0.06
    Act Density 0.006%

    No Known Activations