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

    Neuronpedia

    INDEX
    Explanations

    Creative Writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     célib
    -0.08
    .Sprintf
    -0.07
     тран
    -0.07
    (columns
    -0.06
    .contract
    -0.06
    .format
    -0.06
     dışında
    -0.06
    Hook
    -0.06
    pain
    -0.06
     keys
    -0.06
    POSITIVE LOGITS
     Scholars
    0.06
     Germ
    0.06
    :[
    0.06
     Rap
    0.06
     Isl
    0.06
    ंगल
    0.06
    -national
    0.06
     Excellent
    0.06
    Eric
    0.06
    Chi
    0.06
    Act Density 0.036%

    No Known Activations