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

    Neuronpedia

    INDEX
    Explanations

    lies and manipulation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    igidbody
    -0.07
    าจาก
    -0.07
    ermal
    -0.06
    Jacob
    -0.06
    ZH
    -0.06
    Callable
    -0.06
     самом
    -0.06
    ario
    -0.06
     tanggal
    -0.06
     Rigidbody
    -0.06
    POSITIVE LOGITS
     �
    0.07
    .pdf
    0.07
    紫
    0.07
     허
    0.07
     É
    0.06
    ][/
    0.06
    )didReceiveMemoryWarning
    0.06
     Britann
    0.06
     entitlement
    0.06
     sensation
    0.06
    Act Density 0.027%

    No Known Activations