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

    Neuronpedia

    INDEX
    Explanations

    knowledge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DAN
    -0.07
    増
    -0.07
    Material
    -0.07
    DRV
    -0.07
     Laos
    -0.06
    Appearance
    -0.06
    -0.06
     �
    -0.06
     lavoro
    -0.06
    .motion
    -0.06
    POSITIVE LOGITS
     awareness
    0.07
    erdings
    0.07
     knowing
    0.07
    _lengths
    0.06
    yslu
    0.06
    ج
    0.06
     influencers
    0.06
     Agents
    0.06
     konut
    0.06
     deals
    0.06
    Act Density 0.046%

    No Known Activations