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

    Neuronpedia

    INDEX
    Explanations

    technical data and references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edeki
    -0.06
     hoof
    -0.06
     Alcohol
    -0.06
     品
    -0.06
    Track
    -0.06
     :|:
    -0.06
     �
    -0.06
     serif
    -0.06
    .te
    -0.06
     Cutting
    -0.06
    POSITIVE LOGITS
     ah
    0.07
     pc
    0.06
    State
    0.06
     conspiracy
    0.06
    current
    0.06
    	state
    0.06
     emperor
    0.06
    enght
    0.06
     Homeland
    0.06
    ATS
    0.06
    Act Density 0.014%

    No Known Activations