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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TX
    -0.07
     EH
    -0.06
    �
    -0.06
     放
    -0.06
     Ivan
    -0.06
    資
    -0.06
     cortisol
    -0.06
     departamento
    -0.06
     hiring
    -0.06
    google
    -0.06
    POSITIVE LOGITS
    **(
    0.10
    Guid
    0.07
    BOOT
    0.07
    Birthday
    0.06
    Air
    0.06
     im
    0.06
     Coalition
    0.06
    ?(
    0.06
    ợ
    0.06
    还有
    0.06
    Act Density 0.001%

    No Known Activations