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

    Neuronpedia

    INDEX
    Explanations

    values and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ballads
    0.76
    ifolds
    0.75
     outings
    0.73
     cheeses
    0.72
    ifères
    0.71
    pillars
    0.70
    amides
    0.69
     luận
    0.68
    opi
    0.68
     comforts
    0.68
    POSITIVE LOGITS
     value
    0.82
     version
    0.82
     values
    0.77
    ness
    0.75
    ವಾದ
    0.68
    情况下
    0.67
     information
    0.65
     combination
    0.64
     homogeneous
    0.63
    值为
    0.63
    Act Density 0.508%

    No Known Activations