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

    Neuronpedia

    INDEX
    Explanations

    unnoticeable, invisible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    frau
    -0.07
    пра
    -0.07
    ılış
    -0.07
    ????????
    -0.06
    Two
    -0.06
     eks
    -0.06
    happy
    -0.06
    Sim
    -0.06
    Attack
    -0.06
     tří
    -0.06
    POSITIVE LOGITS
     honestly
    0.07
     document
    0.07
    .Job
    0.06
    	window
    0.06
    _REMOTE
    0.06
     indicates
    0.06
     �
    0.06
    _subset
    0.06
    ALLY
    0.06
    owment
    0.06
    Act Density 0.021%

    No Known Activations