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

    Neuronpedia

    INDEX
    Explanations

    about us page

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     indicador
    0.39
    が大きい
    0.38
    Examples
    0.37
     एग्जांपल
    0.37
     communes
    0.37
     examples
    0.36
     unified
    0.36
     كله
    0.36
    agad
    0.36
     todas
    0.36
    POSITIVE LOGITS
     Us
    0.73
     About
    0.66
    Us
    0.61
    About
    0.59
     Myself
    0.59
     us
    0.58
     Ours
    0.57
     Me
    0.52
     Our
    0.50
     Mission
    0.50
    Act Density 0.005%

    No Known Activations