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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %d
    -0.06
    анной
    -0.06
     �
    -0.06
     deleteUser
    -0.06
     diag
    -0.06
    aks
    -0.06
    AV
    -0.06
     тай
    -0.06
     dignity
    -0.06
    iagnostics
    -0.06
    POSITIVE LOGITS
     manic
    0.07
     incompetent
    0.07
     embarked
    0.07
    .reward
    0.06
    coil
    0.06
     Wonderful
    0.06
     disadv
    0.06
    (css
    0.06
    ettel
    0.06
     Amelia
    0.06
    Act Density 0.010%

    No Known Activations