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

    Neuronpedia

    INDEX
    Explanations

    numerical/identifier codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     epidemic
    -0.07
    -0.07
    ين
    -0.06
    tiv
    -0.06
    规范
    -0.06
    อเม
    -0.06
    _OFFSET
    -0.06
     intention
    -0.06
    -vis
    -0.06
     نفس
    -0.06
    POSITIVE LOGITS
     lodged
    0.07
    ｗ
    0.06
    *I
    0.06
    lider
    0.06
    _REF
    0.06
    œ
    0.06
     ])↵↵
    0.06
    uctor
    0.06
    (separator
    0.06
     '#'
    0.06
    Act Density 0.007%

    No Known Activations