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

    Neuronpedia

    INDEX
    Explanations

    Ch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    insula
    -0.07
    ramework
    -0.07
    ortality
    -0.06
                ↵↵
    -0.06
     arc
    -0.06
     amazed
    -0.06
    until
    -0.06
    endez
    -0.06
    لق
    -0.06
     ruins
    -0.06
    POSITIVE LOGITS
    (tt
    0.07
    成员
    0.07
     consumes
    0.06
     피
    0.06
     robust
    0.06
    Song
    0.06
    .ts
    0.06
    (dy
    0.06
    .JsonIgnore
    0.06
    .tr
    0.06
    Act Density 0.005%

    No Known Activations