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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     maze
    -0.07
     �
    -0.07
    _seen
    -0.07
    REATE
    -0.06
    Booking
    -0.06
     statues
    -0.06
    ATAL
    -0.06
     GPA
    -0.06
    (forKey
    -0.06
     lda
    -0.06
    POSITIVE LOGITS
    Monitoring
    0.07
     coherence
    0.06
     ];
↵
    0.06
     safeg
    0.06
     licence
    0.06
     :"
    0.06
    &lt
    0.06
     incorporated
    0.06
     sequential
    0.06
    芬
    0.06
    Act Density 0.195%

    No Known Activations