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

    Neuronpedia

    INDEX
    Explanations

    creating, obtaining, or installing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    served
    0.47
     gathered
    0.46
     undergoes
    0.46
     reread
    0.46
     converge
    0.45
    вшийся
    0.45
     graze
    0.45
     rise
    0.45
    compute
    0.45
    bind
    0.44
    POSITIVE LOGITS
     installing
    1.59
     getting
    1.59
     selecting
    1.52
     accessing
    1.50
     putting
    1.47
     choosing
    1.47
     creating
    1.46
     obtaining
    1.45
     constructing
    1.45
     submitting
    1.45
    Act Density 0.182%

    No Known Activations