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

    Neuronpedia

    INDEX
    Explanations

    backstory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     SIDE
    -0.07
     Broken
    -0.07
     Projectile
    -0.07
    Fil
    -0.07
    URNS
    -0.07
     filthy
    -0.07
     PIPE
    -0.06
    MED
    -0.06
    OWN
    -0.06
    NT
    -0.06
    POSITIVE LOGITS
     acquisitions
    0.06
     sağlam
    0.06
     cố
    0.06
    _union
    0.06
     tahun
    0.06
     ανα
    0.06
    �
    0.06
    ================================================================================
    0.06
     regs
    0.06
     neod
    0.06
    Act Density 0.004%

    No Known Activations