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

    Neuronpedia

    INDEX
    Explanations

    hooks for state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BSD
    0.41
     PCB
    0.38
    liked
    0.38
     Whitehall
    0.37
     Mohawk
    0.37
     गौरी
    0.36
     Mohr
    0.36
     Xét
    0.35
    auteur
    0.35
     Grayson
    0.35
    POSITIVE LOGITS
    钩
    0.39
     tamamen
    0.38
     completamente
    0.37
     natura
    0.37
     Aspir
    0.37
    cando
    0.37
     полностью
    0.36
     ré
    0.36
     alqu
    0.36
    itness
    0.35
    Act Density 0.000%

    No Known Activations