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

    Neuronpedia

    INDEX
    Explanations

    metal components

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lename
    -0.30
    /Area
    -0.28
    tright
    -0.26
    ãĤ
    -0.25
    çŃ¼
    -0.25
    å°±ä¸į
    -0.25
     flank
    -0.24
    _coords
    -0.24
    OPY
    -0.24
    -dr
    -0.23
    POSITIVE LOGITS
    wt
    0.27
    icker
    0.26
    æ´¥
    0.25
    è´¬åĢ¼
    0.25
     ok
    0.25
    ok
    0.24
    /Search
    0.24
     minister
    0.24
    éĺ¶æ®µ
    0.24
    (branch
    0.23
    Act Density 0.001%

    No Known Activations