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

    Neuronpedia

    INDEX
    Explanations

    Access, Accessibility, Accessible

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ሂ
    0.46
     pushed
    0.42
     Strikes
    0.40
     neben
    0.40
     వార్
    0.40
     HF
    0.39
     sûr
    0.39
     குறைவாக
    0.38
     warned
    0.38
     кры
    0.38
    POSITIVE LOGITS
    Access
    0.50
     Access
    0.46
    Accessible
    0.44
     Acces
    0.40
     Accessible
    0.40
    etam
    0.39
     trit
    0.37
    ার্থীর
    0.37
     Accessibility
    0.37
     forbind
    0.37
    Act Density 0.001%

    No Known Activations