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

    Neuronpedia

    INDEX
    Explanations

    which

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rubble
    -0.07
     Saras
    -0.06
     �
    -0.06
     Alberta
    -0.06
     deren
    -0.06
    Apellido
    -0.06
     geen
    -0.06
     Saudis
    -0.05
    แก
    -0.05
    Georgia
    -0.05
    POSITIVE LOGITS
    [N
    0.07
    DDevice
    0.07
    697
    0.06
     gettimeofday
    0.06
     hö
    0.06
    virtual
    0.06
    .imwrite
    0.06
    _coll
    0.06
    _eq
    0.06
     Iso
    0.06
    Act Density 0.066%

    No Known Activations