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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    劲
    -0.07
     כמה
    -0.07
    spawn
    -0.07
     Madd
    -0.07
     circ
    -0.07
    .auth
    -0.07
    	dispatch
    -0.07
    TextChanged
    -0.07
     Dix
    -0.07
     attached
    -0.07
    POSITIVE LOGITS
    GIT
    0.07
    .pid
    0.07
    💩
    0.07
     телеф
    0.07
     vb
    0.07
    南山
    0.07
     supervisor
    0.07
     LOS
    0.06
    hei
    0.06
    pees
    0.06
    Act Density 0.001%

    No Known Activations