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

    Neuronpedia

    INDEX
    Explanations

    learning how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    such
    0.48
    Activated
    0.47
    Méd
    0.46
    цен
    0.45
    URANCE
    0.45
    KNOWN
    0.45
    USED
    0.44
    Requested
    0.44
    Ｕ
    0.44
    Ep
    0.44
    POSITIVE LOGITS
     on
    0.49
    ank
    0.48
    idae
    0.48
     intangible
    0.48
     to
    0.47
    ists
    0.47
     habit
    0.46
    ilst
    0.45
     habits
    0.45
     instincts
    0.45
    Act Density 0.001%

    No Known Activations