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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AFP
    -0.07
     endiş
    -0.07
     detectives
    -0.06
     succeeded
    -0.06
     Off
    -0.06
     tàu
    -0.06
     méd
    -0.06
    .getParent
    -0.06
     indict
    -0.06
     McCain
    -0.06
    POSITIVE LOGITS
    This
    0.12
     This
    0.10
    "This
    0.08
    ricing
    0.07
     mats
    0.07
    “This
    0.07
     this
    0.07
    оры
    0.07
    this
    0.07
    rana
    0.07
    Act Density 0.004%

    No Known Activations