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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -trigger
    -0.07
     prostitute
    -0.06
    гає
    -0.06
    gia
    -0.06
     loading
    -0.06
    urrence
    -0.06
     br
    -0.06
     wires
    -0.06
     shifts
    -0.06
     Ports
    -0.06
    POSITIVE LOGITS
    .cum
    0.06
    .Generic
    0.06
    .Se
    0.06
    .partner
    0.06
    .SizeMode
    0.06
     стала
    0.06
     SingleChildScrollView
    0.06
    /colors
    0.06
    .Transfer
    0.06
    [F
    0.06
    Act Density 0.118%

    No Known Activations