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

    Neuronpedia

    INDEX
    Explanations

    compound noun phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prens
    0.39
    ISH
    0.37
     zaidi
    0.37
     princip
    0.37
     princ
    0.36
     remplir
    0.36
     wing
    0.36
     ettevõ
    0.36
     sít
    0.36
     stim
    0.35
    POSITIVE LOGITS
    內的
    0.39
    urar
    0.39
     музыку
    0.38
     পানি
    0.37
     inteiro
    0.37
    marginLeft
    0.37
     bialgebras
    0.37
     निवडणु
    0.37
     nitrates
    0.37
     खुदाई
    0.36
    Act Density 0.103%

    No Known Activations