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

    Neuronpedia

    INDEX
    Explanations

    Text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ranges
    -0.07
    .CENTER
    -0.07
     truth
    -0.06
    स
    -0.06
     المو
    -0.06
    reek
    -0.06
    oleans
    -0.06
     元
    -0.06
    _mo
    -0.06
    .phase
    -0.06
    POSITIVE LOGITS
    τς
    0.07
     fors
    0.06
     ARP
    0.06
    립니다
    0.06
     withdrawn
    0.06
     DSM
    0.06
    (Student
    0.06
     naw
    0.06
     kultur
    0.06
    (IntPtr
    0.06
    Act Density 0.001%

    No Known Activations