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

    Neuronpedia

    INDEX
    Explanations

    Code/Technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trash
    -0.07
     Naz
    -0.07
     Aleks
    -0.06
     Sid
    -0.06
     Romanian
    -0.06
     philosoph
    -0.06
     blamed
    -0.06
     objet
    -0.06
     CEO
    -0.06
     Rab
    -0.06
    POSITIVE LOGITS
    .enqueue
    0.06
     salmon
    0.06
     arrangements
    0.06
    检测
    0.06
     motivating
    0.06
    (pkg
    0.06
     routinely
    0.06
     Closed
    0.06
     involved
    0.06
    �
    0.06
    Act Density 0.000%

    No Known Activations