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

    Neuronpedia

    INDEX
    Explanations

    Meals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     glance
    -0.08
     देखकर
    -0.08
     anticipation
    -0.08
     خطر
    -0.08
    _finalize
    -0.08
     agility
    -0.07
     allowed
    -0.07
     epidemi
    -0.07
    IONAL
    -0.07
     endings
    -0.07
    POSITIVE LOGITS
    铭
    0.09
    Roof
    0.08
    'homme
    0.08
     sedan
    0.08
     roof
    0.08
    _LICENSE
    0.08
     Frühstück
    0.08
     osobe
    0.08
    దేశ
    0.08
    \Data
    0.07
    Act Density 0.012%

    No Known Activations