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

    Neuronpedia

    INDEX
    Explanations

    Data, users, people

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     this
    -0.13
     these
    -0.10
     THIS
    -0.09
    This
    -0.09
     This
    -0.09
    	this
    -0.07
     These
    -0.07
    .This
    -0.07
    this
    -0.07
    angelog
    -0.07
    POSITIVE LOGITS
     scratch
    0.07
    hari
    0.06
    Monitoring
    0.06
    Successfully
    0.06
    _human
    0.06
    utherford
    0.06
    expert
    0.06
     Strip
    0.06
     tersebut
    0.06
    Scr
    0.06
    Act Density 0.130%

    No Known Activations