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

    Neuronpedia

    INDEX
    Explanations

    available

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     είναι
    -0.08
     Preview
    -0.07
    ！↵↵
    -0.07
     이러
    -0.07
    αρ
    -0.07
    zd
    -0.07
    usted
    -0.06
     나라
    -0.06
    írk
    -0.06
    ử
    -0.06
    POSITIVE LOGITS
    _processes
    0.07
    PU
    0.06
     pounding
    0.06
    �
    0.06
     Trent
    0.06
    _cliente
    0.06
    том
    0.06
    Daemon
    0.06
     unborn
    0.06
     Cam
    0.06
    Act Density 0.025%

    No Known Activations