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

    Neuronpedia

    INDEX
    Explanations

    legal terms and conditions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     appealing
    -0.07
     Artifact
    -0.06
     query
    -0.06
    %");↵
    -0.06
     forwards
    -0.06
     první
    -0.06
     Variety
    -0.06
     Rece
    -0.06
     Memories
    -0.06
     Se
    -0.06
    POSITIVE LOGITS
     đ
    0.07
     달
    0.07
    Pick
    0.06
     оно
    0.06
    licer
    0.06
    ülen
    0.06
    -gl
    0.06
     tailor
    0.06
     vyb
    0.06
     sagte
    0.06
    Act Density 0.006%

    No Known Activations