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

    Neuronpedia

    INDEX
    Explanations

    cabanas, bandanas, palapas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rushing
    0.43
    ící
    0.40
    AttrName
    0.40
     गुण
    0.39
     ruffled
    0.38
     rushed
    0.37
     Appliances
    0.37
    GUN
    0.36
     வளாக
    0.36
     propriedade
    0.36
    POSITIVE LOGITS
     cab
    0.98
     Cab
    0.78
    Cab
    0.77
    cab
    0.70
     CAB
    0.61
     pavilion
    0.58
    CAB
    0.58
     cabs
    0.57
     pavilions
    0.54
     PAV
    0.50
    Act Density 0.002%

    No Known Activations