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
    ปร
    -0.07
     company
    -0.07
    312
    -0.07
     designed
    -0.07
     speeches
    -0.07
     coff
    -0.06
    690
    -0.06
    813
    -0.06
     climbing
    -0.06
     real
    -0.06
    POSITIVE LOGITS
    深圳
    0.07
     [(
    0.07
    وذ
    0.07
    +"/"+
    0.07
     erót
    0.07
    (!(
    0.06
    Erot
    0.06
    haven
    0.06
    adoo
    0.06
     سرد
    0.06
    Act Density 0.006%

    No Known Activations