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

    Neuronpedia

    INDEX
    Explanations

    .pyplot

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "strconv
    -0.06
    INCLUDED
    -0.06
     teachers
    -0.06
    _operator
    -0.06
     stavu
    -0.06
    Hamilton
    -0.06
     qua
    -0.06
     holder
    -0.06
    .beans
    -0.06
     Expenses
    -0.06
    POSITIVE LOGITS
     Reliable
    0.08
    kaar
    0.07
     dokun
    0.07
    	router
    0.07
    REP
    0.07
    ",&
    0.07
     Irving
    0.07
    良
    0.06
    /pp
    0.06
     devel
    0.06
    Act Density 0.001%

    No Known Activations