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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    or
    -0.07
     ап
    -0.07
    Од
    -0.07
     и
    -0.07
    (team
    -0.06
    --------------↵
    -0.06
    --↵↵
    -0.06
     لكن
    -0.06
    >_
    -0.06
     поп
    -0.06
    POSITIVE LOGITS
     Towards
    0.06
    ='$
    0.06
     RMS
    0.06
    ceptive
    0.06
     úspěš
    0.06
    .flash
    0.06
     eigenen
    0.05
    sequential
    0.05
    esthes
    0.05
     locate
    0.05
    Act Density 0.001%

    No Known Activations