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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ltd
    -0.06
     birden
    -0.06
     ταιν
    -0.06
    ически
    -0.05
    	day
    -0.05
    wright
    -0.05
    isos
    -0.05
     xx
    -0.05
     Hosp
    -0.05
     blueprint
    -0.05
    POSITIVE LOGITS
    linger
    0.07
    .ant
    0.07
     remodel
    0.07
     Friedman
    0.07
    babel
    0.06
     hinges
    0.06
     стану
    0.06
     interior
    0.06
     From
    0.06
    .Comp
    0.06
    Act Density 0.000%

    No Known Activations