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

    Neuronpedia

    INDEX
    Explanations

    Events and performances

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Theater
    -0.06
     mysteries
    -0.06
    "errors
    -0.06
    vasive
    -0.06
    城市
    -0.06
    раст
    -0.06
    管
    -0.06
     كن
    -0.06
     identifying
    -0.06
    Recorder
    -0.06
    POSITIVE LOGITS
    _DOT
    0.07
    ㅠㅠ
    0.07
     vtx
    0.06
     Loài
    0.06
    (IF
    0.06
    embre
    0.06
     spell
    0.06
     MUST
    0.06
    .strip
    0.06
    ibold
    0.06
    Act Density 0.098%

    No Known Activations