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

    Neuronpedia

    INDEX
    Explanations

    rabbit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     PowerShell
    -0.07
     executives
    -0.07
     XS
    -0.07
    _NE
    -0.07
     CFO
    -0.07
    Power
    -0.07
    .HasKey
    -0.07
     phrase
    -0.07
    368
    -0.07
    _TIMEOUT
    -0.06
    POSITIVE LOGITS
     Rabbit
    0.13
     rabbit
    0.12
     rabbits
    0.12
     Rab
    0.08
     nag
    0.07
    rabbit
    0.07
    abbit
    0.07
     Bunny
    0.07
    秋
    0.07
    .rabbit
    0.06
    Act Density 0.004%

    No Known Activations