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

    Neuronpedia

    INDEX
    Explanations

    ground

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     spas
    -0.07
     separation
    -0.06
     sample
    -0.06
     nug
    -0.06
    ANCE
    -0.06
    озможно
    -0.06
     usually
    -0.06
    áků
    -0.06
     splice
    -0.06
     knack
    -0.06
    POSITIVE LOGITS
     Terrain
    0.09
     Ground
    0.08
     Terra
    0.08
     terrain
    0.07
     ground
    0.07
     terra
    0.07
    Ground
    0.07
     zeměděl
    0.07
     territory
    0.07
     territories
    0.07
    Act Density 0.021%

    No Known Activations