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

    Neuronpedia

    INDEX
    Explanations

    edit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственным
    -0.09
    னால்
    -0.08
     کو
    -0.08
     emailed
    -0.08
    унд
    -0.07
    गार
    -0.07
     implanted
    -0.07
    umme
    -0.07
     vecka
    -0.07
     noche
    -0.07
    POSITIVE LOGITS
    、新
    0.08
    �
    0.08
    /delete
    0.08
     Minerals
    0.08
     Terraform
    0.08
    Mine
    0.08
     Lifecycle
    0.07
    =function
    0.07
     生命周期
    0.07
    IRTH
    0.07
    Act Density 0.016%

    No Known Activations