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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	Time
    -0.07
     QS
    -0.06
     gd
    -0.06
    .pet
    -0.06
    _dll
    -0.06
     luận
    -0.06
    \Core
    -0.06
     cán
    -0.05
     Hopkins
    -0.05
     ///</
    -0.05
    POSITIVE LOGITS
    _NON
    0.07
    Users
    0.07
     throat
    0.07
    MAKE
    0.07
     Compared
    0.07
    Claim
    0.06
     potency
    0.06
    _CRYPTO
    0.06
    рос
    0.06
    OSH
    0.06
    Act Density 0.052%

    No Known Activations