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

    Neuronpedia

    INDEX
    Explanations

    infidelity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     provisioning
    -0.06
     revolves
    -0.06
     GTA
    -0.06
    .PREFERRED
    -0.06
    ovie
    -0.06
    .transparent
    -0.06
     med
    -0.06
     ngx
    -0.06
    cont
    -0.06
     prosecuting
    -0.06
    POSITIVE LOGITS
     @"\
    0.07
     foods
    0.07
    uhe
    0.06
     Ellis
    0.06
     erupt
    0.06
     inflation
    0.06
    ­s
    0.06
    ellery
    0.06
     tags
    0.06
    чя
    0.06
    Act Density 0.032%

    No Known Activations