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

    Neuronpedia

    INDEX
    Explanations

    literary Gatsby striving and obsessive

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Various
    0.41
     Diam
    0.41
    ITOR
    0.37
    Diam
    0.37
    peror
    0.36
     Antibody
    0.36
     diam
    0.36
     Subsequently
    0.36
     oxidase
    0.35
     oops
    0.35
    POSITIVE LOGITS
    僄
    0.40
     पसंद
    0.38
     보면은
    0.38
     લી
    0.38
    sensitive
    0.37
     반응
    0.37
     સારું
    0.37
    Sensitive
    0.36
    elernt
    0.36
     lovely
    0.36
    Act Density 0.000%

    No Known Activations