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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provinc
    -0.07
     отнош
    -0.07
    ठन
    -0.06
    佐
    -0.06
    期间
    -0.06
     skeletons
    -0.06
     Со
    -0.06
    :</
    -0.06
    즈
    -0.06
    LOC
    -0.06
    POSITIVE LOGITS
    ARCH
    0.07
    /pay
    0.07
    (!_
    0.07
     Medal
    0.07
     posted
    0.06
     droit
    0.06
     masturbation
    0.06
    \.
    0.06
     pledged
    0.06
    []=$
    0.06
    Act Density 0.013%

    No Known Activations