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

    Neuronpedia

    INDEX
    Explanations

    Legal cases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Al
    -0.06
     movies
    -0.06
     melody
    -0.06
     curves
    -0.06
    ,J
    -0.06
     ew
    -0.06
     blackmail
    -0.05
     malware
    -0.05
    igr
    -0.05
    Charge
    -0.05
    POSITIVE LOGITS
    /Auth
    0.08
     вт
    0.07
    -transparent
    0.07
    ukkit
    0.07
    目前
    0.07
    TA
    0.07
    ัน
    0.07
    経
    0.07
    页面存档备份
    0.06
     treatments
    0.06
    Act Density 0.006%

    No Known Activations