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

    Neuronpedia

    INDEX
    Explanations

    Hitting a wall/roadblock

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flt
    -0.07
    ibar
    -0.07
    ilm
    -0.07
    lope
    -0.07
     insights
    -0.07
     اجر
    -0.06
    站
    -0.06
     filtered
    -0.06
    236
    -0.06
    bindings
    -0.06
    POSITIVE LOGITS
     weren
    0.07
    (INVOKE
    0.07
    ุตสาหกรรม
    0.07
    �
    0.07
     arous
    0.06
    ımızın
    0.06
     SUB
    0.06
     lxml
    0.06
     reconstruct
    0.06
     مر
    0.06
    Act Density 0.052%

    No Known Activations