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

    Neuronpedia

    INDEX
    Explanations

    activation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .loadtxt
    -0.07
     disagree
    -0.07
    /firebase
    -0.07
    .StatusOK
    -0.07
    אנגל
    -0.07
    xxxxxxxx
    -0.07
    有网友
    -0.06
    喝茶
    -0.06
    参加会议
    -0.06
    json
    -0.06
    POSITIVE LOGITS
     },↵↵
    0.08
     defeat
    0.07
    .hit
    0.07
    伪
    0.07
     temperament
    0.07
     doom
    0.07
     emulation
    0.06
    (()=>
    0.06
     escrit
    0.06
     dzieci
    0.06
    Act Density 0.006%

    No Known Activations