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

    Neuronpedia

    INDEX
    Explanations

    lists of things

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alo
    -0.06
     sew
    -0.06
     yardım
    -0.06
     Bey
    -0.06
     seedu
    -0.06
    άλυ
    -0.06
    -ms
    -0.06
    よ
    -0.06
     cha
    -0.06
     incest
    -0.06
    POSITIVE LOGITS
     suspect
    0.07
     preceding
    0.07
    ICS
    0.06
    .Matrix
    0.06
     bottles
    0.06
    /kernel
    0.06
    139
    0.06
    LOCATION
    0.06
    Cooldown
    0.06
    150
    0.06
    Act Density 0.000%

    No Known Activations