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

    Neuronpedia

    INDEX
    Explanations

    promote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    én
    -0.07
     Cases
    -0.07
     perg
    -0.07
     crews
    -0.06
    τογραφ
    -0.06
    _created
    -0.06
     cracks
    -0.06
     beams
    -0.06
     injuries
    -0.06
     MATERIAL
    -0.06
    POSITIVE LOGITS
    евой
    0.06
    .groupby
    0.06
    δ
    0.06
     verbess
    0.06
    	Return
    0.06
     提
    0.06
     것이
    0.06
    とした
    0.06
     overwrite
    0.06
    cej
    0.06
    Act Density 0.010%

    No Known Activations