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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     originals
    -0.06
    SEM
    -0.06
     FTP
    -0.06
     RW
    -0.06
     infantry
    -0.06
     velocities
    -0.06
     cooled
    -0.06
    设施
    -0.06
     milestone
    -0.06
    stial
    -0.06
    POSITIVE LOGITS
    (atom
    0.07
    ektedir
    0.07
     interv
    0.07
    _npc
    0.06
    SuppressLint
    0.06
    chai
    0.06
    .Infrastructure
    0.06
    .preventDefault
    0.06
     celle
    0.06
    切り
    0.06
    Act Density 0.001%

    No Known Activations