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

    Neuronpedia

    INDEX
    Explanations

    addiction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     københavn
    -0.07
    jíž
    -0.06
    رير
    -0.06
     biopsy
    -0.06
    評
    -0.06
    setw
    -0.06
    olah
    -0.06
    อำนวย
    -0.06
     Swal
    -0.06
     Kyle
    -0.06
    POSITIVE LOGITS
     addiction
    0.11
     asoci
    0.08
    PTY
    0.07
    JI
    0.07
    ASIC
    0.06
     Constit
    0.06
     }}↵↵
    0.06
     monoc
    0.06
     okum
    0.06
     additive
    0.06
    Act Density 0.007%

    No Known Activations