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

    Neuronpedia

    INDEX
    Explanations

    also

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pollution
    -0.07
     Users
    -0.06
     Katz
    -0.06
     CentOS
    -0.06
    	want
    -0.06
    Todd
    -0.06
     OpenSSL
    -0.06
     nationality
    -0.06
    Jennifer
    -0.06
     prisoners
    -0.06
    POSITIVE LOGITS
    -pt
    0.07
    ุท
    0.07
     eventData
    0.06
    -dd
    0.06
    -all
    0.06
     می
    0.06
    雑
    0.06
    FLICT
    0.06
    -prepend
    0.06
    /pl
    0.06
    Act Density 0.005%

    No Known Activations