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

    Neuronpedia

    INDEX
    Explanations

    task and target names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    >\<^
    0.43
     भंडार
    0.41
    𝐠
    0.41
    шымта
    0.41
     होना
    0.40
     thermocouple
    0.39
    usermodel
    0.39
     спи
    0.39
     thermocou
    0.39
     PCE
    0.38
    POSITIVE LOGITS
    registerTask
    0.52
     cher
    0.44
     Aufgabe
    0.44
     sustenance
    0.44
     palab
    0.43
     Estos
    0.43
     Aufgaben
    0.43
     upang
    0.42
     wants
    0.41
     productive
    0.41
    Act Density 0.003%

    No Known Activations