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

    Neuronpedia

    INDEX
    Explanations

    just

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arac
    -0.07
     Nej
    -0.06
    _ATTACH
    -0.06
     شاید
    -0.06
    Од
    -0.06
     Frid
    -0.06
    _STA
    -0.06
    ">';↵
    -0.06
     *)&
    -0.06
    _wf
    -0.06
    POSITIVE LOGITS
    /screen
    0.07
     Coffee
    0.07
     Cornell
    0.07
    -move
    0.07
    message
    0.07
     Smith
    0.07
     ALWAYS
    0.06
    목
    0.06
     sociology
    0.06
     Народ
    0.06
    Act Density 0.000%

    No Known Activations