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

    Neuronpedia

    INDEX
    Explanations

    directions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Session
    -0.07
     cuatro
    -0.07
    fmt
    -0.06
     �
    -0.06
     yetiş
    -0.06
    urope
    -0.06
    -md
    -0.06
    ramid
    -0.06
     Ef
    -0.06
    国内
    -0.06
    POSITIVE LOGITS
    خش
    0.07
    .Offset
    0.07
     Clash
    0.07
    qui
    0.06
     distressed
    0.06
     adjustable
    0.06
    ใส
    0.06
     paranoia
    0.06
     Rabbi
    0.06
    opc
    0.06
    Act Density 0.031%

    No Known Activations