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

    Neuronpedia

    INDEX
    Explanations

    Programming and linguistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     seat
    -0.06
    ooo
    -0.06
    uran
    -0.06
     її
    -0.06
     GetAll
    -0.06
    Content
    -0.06
    	ms
    -0.06
     trophy
    -0.06
    FPS
    -0.05
     sts
    -0.05
    POSITIVE LOGITS
    aire
    0.08
    ��
    0.08
     Macron
    0.07
    VEN
    0.07
    CEPTION
    0.07
    CALE
    0.06
    antaged
    0.06
    gerald
    0.06
     mathematic
    0.06
    ERVED
    0.06
    Act Density 0.023%

    No Known Activations