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
    (hr
    -0.07
    aseña
    -0.07
    -archive
    -0.06
     стану
    -0.06
    さ
    -0.06
    erreur
    -0.06
     chr
    -0.06
    vehicles
    -0.06
    <r
    -0.06
    setAttribute
    -0.06
    POSITIVE LOGITS
     hubby
    0.07
     unjust
    0.07
    modifier
    0.06
    NEY
    0.06
    lock
    0.06
     insign
    0.06
     dung
    0.06
    _iface
    0.06
     Rot
    0.06
     NOTICE
    0.06
    Act Density 0.030%

    No Known Activations