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

    Neuronpedia

    INDEX
    Explanations

    Do not leave unattended

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iley
    -0.08
     untouched
    -0.08
     bewusst
    -0.07
     sanity
    -0.07
    .partition
    -0.07
    -0.07
     freshness
    -0.07
     in
    -0.07
    _node
    -0.07
    _setting
    -0.07
    POSITIVE LOGITS
    ভিড
    0.09
    หาร
    0.08
     rok
    0.08
     breakthroughs
    0.08
    WAY
    0.08
     banc
    0.08
    abt
    0.08
     teacht
    0.08
     رهيو
    0.08
     breakthrough
    0.08
    Act Density 0.001%
    No Known Activations