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
    .bounds
    -0.07
     VR
    -0.07
     meticulous
    -0.07
     труда
    -0.06
     yok
    -0.06
    _TBL
    -0.06
     polynomial
    -0.06
    ystone
    -0.06
    contacts
    -0.06
    -picker
    -0.06
    POSITIVE LOGITS
    قلال
    0.07
     slova
    0.06
    $search
    0.06
     은
    0.06
    quoted
    0.06
     красив
    0.06
    hear
    0.06
     s
    0.06
    (act
    0.06
     zlep
    0.06
    Act Density 0.014%

    No Known Activations