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

    Neuronpedia

    INDEX
    Explanations

    Code/math fragments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     enth
    -0.07
    授
    -0.07
    /login
    -0.07
    .warning
    -0.06
    thank
    -0.06
    fuck
    -0.06
     estates
    -0.06
    äs
    -0.06
     сф
    -0.06
    Bits
    -0.06
    POSITIVE LOGITS
    ',['../
    0.08
    /*******************************************************************************↵
    0.07
     coarse
    0.07
    contained
    0.06
    kového
    0.06
    ])):↵
    0.06
    ])))↵
    0.06
    ▋
    0.06
     olacağ
    0.06
     tumult
    0.06
    Act Density 0.000%

    No Known Activations