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

    Neuronpedia

    INDEX
    Explanations

    ING

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Granted
    -0.07
    -energy
    -0.07
     Transportation
    -0.06
     SendMessage
    -0.06
    �
    -0.06
     }}"↵
    -0.06
     Fighter
    -0.06
     Native
    -0.06
    �
    -0.06
    _CHUNK
    -0.06
    POSITIVE LOGITS
    ❃
    0.07
    Æ
    0.07
    บาคาร
    0.07
     따른
    0.07
    pora
    0.07
    تظ
    0.07
     gadgets
    0.07
     pops
    0.07
    术语
    0.07
     Hol
    0.06
    Act Density 0.000%

    No Known Activations