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

    Neuronpedia

    INDEX
    Explanations

    device configuration and communication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sha
    -0.09
    neau
    -0.08
     Natale
    -0.08
     الحيو
    -0.08
     Ela
    -0.08
     seemingly
    -0.08
    rita
    -0.08
    ி�
    -0.08
    decoded
    -0.07
    สาร
    -0.07
    POSITIVE LOGITS
    -side
    0.10
    側
    0.10
    측
    0.09
     counterpart
    0.09
    .master
    0.08
     পাশে
    0.08
     Matching
    0.07
    /master
    0.07
     empf
    0.07
    .respond
    0.07
    Act Density 0.014%

    No Known Activations