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

    Neuronpedia

    INDEX
    Explanations

    in/if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    violent
    -0.07
     lain
    -0.07
     कल
    -0.07
    UC
    -0.06
    XH
    -0.06
     Mog
    -0.06
    ョ
    -0.06
     кілька
    -0.06
     owners
    -0.06
     méně
    -0.06
    POSITIVE LOGITS
    ats
    0.06
    ests
    0.06
    .hamcrest
    0.06
     Deaths
    0.06
    	define
    0.06
    	channel
    0.06
    temperature
    0.06
     nær
    0.06
     використання
    0.06
     hon
    0.06
    Act Density 0.140%

    No Known Activations