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

    Neuronpedia

    INDEX
    Explanations

    entity followed by action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     operate
    0.64
     Are
    0.58
    nare
    0.55
     pollute
    0.53
    Are
    0.52
     gestire
    0.51
     Lied
    0.51
     Operate
    0.50
    iams
    0.50
     fale
    0.50
    POSITIVE LOGITS
     выяс
    0.50
    लेश्वर
    0.49
     prophyl
    0.49
     объяс
    0.48
    まず
    0.48
    proceed
    0.47
     addresses
    0.47
    Analog
    0.44
     proceeds
    0.44
     recalls
    0.43
    Act Density 0.198%

    No Known Activations