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

    Neuronpedia

    INDEX
    Explanations

    random snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kır
    -0.07
     CFG
    -0.07
    .VISIBLE
    -0.06
    argar
    -0.06
     व
    -0.06
     matrices
    -0.06
     하루
    -0.06
    .mid
    -0.06
    海
    -0.06
     camping
    -0.06
    POSITIVE LOGITS
    Comic
    0.07
     takové
    0.07
    queueReusableCell
    0.07
     Conversely
    0.07
     относ
    0.06
     })}↵
    0.06
    andum
    0.06
     Comic
    0.06
    eating
    0.06
     dele
    0.06
    Act Density 0.365%

    No Known Activations