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

    Neuronpedia

    INDEX
    Explanations

    software versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    atk
    -0.07
    Thr
    -0.07
    insn
    -0.07
    %=
    -0.07
     struggle
    -0.07
     ws
    -0.07
    私下
    -0.07
     VR
    -0.07
    ᄢ
    -0.07
    Mech
    -0.07
    POSITIVE LOGITS
     Park
    0.07
     InvalidArgumentException
    0.07
    纪委监
    0.07
    枹
    0.07
    acts
    0.07
    ам
    0.07
    דבריו
    0.07
    限り
    0.07
    stdarg
    0.06
    AINED
    0.06
    Act Density 0.003%

    No Known Activations