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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    standard
    -0.06
    Four
    -0.06
    equ
    -0.06
     zombie
    -0.06
    sigma
    -0.05
    -information
    -0.05
    ai
    -0.05
     advancements
    -0.05
    Resolution
    -0.05
     stack
    -0.05
    POSITIVE LOGITS
    dım
    0.06
    credentials
    0.06
     bic
    0.06
    651
    0.06
    	Check
    0.06
    diği
    0.06
     biomedical
    0.06
    急
    0.06
    RID
    0.06
     shields
    0.06
    Act Density 0.008%

    No Known Activations