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

    Neuronpedia

    INDEX
    Explanations

    Technical/mathematical language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Orr
    -0.07
     oriented
    -0.07
    .r
    -0.07
    oriented
    -0.06
     जनवर
    -0.06
    sted
    -0.06
    _CH
    -0.06
    /access
    -0.06
    .account
    -0.06
    undaki
    -0.06
    POSITIVE LOGITS
     heatmap
    0.08
    /gtest
    0.07
     Papua
    0.07
    (def
    0.06
    шли
    0.06
    AGMA
    0.06
    申
    0.06
    Destructor
    0.06
     surg
    0.06
     shaky
    0.06
    Act Density 0.241%

    No Known Activations