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

    Neuronpedia

    INDEX
    Explanations

    hours

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belong
    -0.08
     accreditation
    -0.07
     slain
    -0.07
     Reggie
    -0.07
     saying
    -0.07
    .accept
    -0.07
     Mend
    -0.07
     Mann
    -0.06
     deselect
    -0.06
     cmp
    -0.06
    POSITIVE LOGITS
     hours
    0.15
     Hours
    0.14
     Hour
    0.14
     hour
    0.14
    hour
    0.12
    Hours
    0.12
    -hour
    0.11
     hrs
    0.11
    hours
    0.11
    -hours
    0.11
    Act Density 0.029%

    No Known Activations