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

    Neuronpedia

    INDEX
    Explanations

    For

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <D
    -0.06
    摩
    -0.06
    �
    -0.06
    別
    -0.06
    "d
    -0.05
     clips
    -0.05
    hyp
    -0.05
    ilated
    -0.05
    .templates
    -0.05
    'D
    -0.05
    POSITIVE LOGITS
    invite
    0.07
    USIC
    0.07
    (script
    0.07
     Sunderland
    0.07
     Taiwan
    0.07
    лександ
    0.07
     Bazı
    0.07
     Nursery
    0.07
     IntPtr
    0.07
    ********
    0.07
    Act Density 0.001%

    No Known Activations