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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -story
    -0.07
     weekly
    -0.06
     homic
    -0.06
     půj
    -0.06
    Android
    -0.06
    oden
    -0.06
     lombok
    -0.06
    Ts
    -0.06
    クロ
    -0.06
     TXT
    -0.06
    POSITIVE LOGITS
    θερ
    0.06
     kvinner
    0.06
     |=
    0.06
    <ApplicationUser
    0.06
     reliant
    0.06
     indices
    0.06
    SetBranch
    0.06
     stiff
    0.06
    wingConstants
    0.06
    каж
    0.06
    Act Density 0.011%

    No Known Activations