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

    Neuronpedia

    INDEX
    Explanations

    Article photos

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mig
    -0.08
     חוד
    -0.08
     directory
    -0.07
    �
    -0.07
     Chang
    -0.07
    辂
    -0.07
     dept
    -0.07
    (Throwable
    -0.07
     Pep
    -0.07
    _ped
    -0.07
    POSITIVE LOGITS
     entails
    0.08
    (wallet
    0.07
    Baseline
    0.07
     matter
    0.07
    עשו
    0.07
    	Global
    0.07
    arters
    0.07
     analsex
    0.07
     initial
    0.06
    表面
    0.06
    Act Density 0.017%

    No Known Activations