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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kontakt
    -0.06
     Spr
    -0.06
     boiling
    -0.06
     spanning
    -0.06
     lattice
    -0.06
     zw
    -0.05
     Tok
    -0.05
    ktop
    -0.05
    thumbs
    -0.05
     Cry
    -0.05
    POSITIVE LOGITS
    ====
    0.07
     выб
    0.07
    istol
    0.07
    -ev
    0.07
    (__('
    0.07
    ظٹ
    0.06
     EXEMPLARY
    0.06
    013
    0.06
    427
    0.06
    |null
    0.06
    Act Density 0.000%

    No Known Activations