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

    Neuronpedia

    INDEX
    Explanations

    sincere

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     headphones
    -0.06
    FragmentManager
    -0.06
    .Year
    -0.06
     Deutschland
    -0.06
     storing
    -0.06
    rovers
    -0.06
     pady
    -0.06
    [j
    -0.06
    -Headers
    -0.06
     logically
    -0.06
    POSITIVE LOGITS
    exter
    0.07
    SAM
    0.07
    (DialogInterface
    0.07
     �
    0.07
    MK
    0.07
     Sign
    0.07
    Ul
    0.07
    004
    0.07
    (type
    0.07
    YLE
    0.07
    Act Density 0.002%

    No Known Activations