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

    Neuronpedia

    INDEX
    Explanations

    reconcile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .testing
    -0.07
     LZ
    -0.07
     MEMORY
    -0.07
     nehmen
    -0.07
     lament
    -0.07
     عباس
    -0.07
    $,
    -0.06
     Abbas
    -0.06
    FullYear
    -0.06
     Howe
    -0.06
    POSITIVE LOGITS
     uncomp
    0.06
     пла
    0.06
     Ay
    0.06
    conc
    0.06
     �
    0.06
     Mahar
    0.06
     reimbursement
    0.06
     conform
    0.06
    sq
    0.06
    ==↵
    0.06
    Act Density 0.003%

    No Known Activations