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

    Neuronpedia

    INDEX
    Explanations

    Code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gmail
    -0.07
    災
    -0.06
    암
    -0.06
     Bài
    -0.06
     incent
    -0.06
     adults
    -0.06
    aghetti
    -0.06
    ाजन
    -0.06
     Clip
    -0.06
    يمة
    -0.06
    POSITIVE LOGITS
    .control
    0.06
    :"
    0.06
    Repeated
    0.06
    IRCLE
    0.06
     '-
    0.06
    omm
    0.06
    AL
    0.06
    	Spring
    0.06
     комму
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations