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

    Neuronpedia

    INDEX
    Explanations

    moved

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    273
    -0.07
     manipulated
    -0.07
    lete
    -0.06
    瑞
    -0.06
     curve
    -0.06
    ंटर
    -0.06
     Parser
    -0.06
    běh
    -0.06
     tedavi
    -0.06
    eeper
    -0.06
    POSITIVE LOGITS
     tri
    0.06
    �u
    0.06
     sg
    0.06
     „
    0.06
    {text
    0.06
    .activation
    0.06
     προσ
    0.06
     مقر
    0.06
     tôi
    0.06
     cq
    0.06
    Act Density 0.022%

    No Known Activations