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

    Neuronpedia

    INDEX
    Explanations

    location prepositions like 'in'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     immunological
    0.47
     hypotheses
    0.42
     immunology
    0.42
     stressors
    0.40
     hypothesis
    0.38
     reformulation
    0.38
     immuno
    0.37
    餑
    0.37
     resumption
    0.35
     diagnoses
    0.35
    POSITIVE LOGITS
     valleys
    0.56
     trenches
    0.54
     ditches
    0.54
     caves
    0.54
     confines
    0.51
     prostor
    0.51
     sandbox
    0.50
     prostoru
    0.50
     пространство
    0.49
     prostředí
    0.49
    Act Density 0.133%

    No Known Activations