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

    Neuronpedia

    INDEX
    Explanations

    array

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tan
    -0.08
     filmed
    -0.07
     chai
    -0.06
     차
    -0.06
    VD
    -0.06
    aja
    -0.06
    ière
    -0.06
    InThe
    -0.06
    (/^\
    -0.06
    ând
    -0.06
    POSITIVE LOGITS
    //----------------------------------------------------------------------------↵
    0.07
     Carrie
    0.07
     aspir
    0.06
     perv
    0.06
     vale
    0.06
     subscri
    0.06
    .Struct
    0.06
     Cly
    0.06
     unknow
    0.06
     อย
    0.06
    Act Density 0.005%

    No Known Activations