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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tumors
    -0.07
    (#)
    -0.07
    ibir
    -0.07
    ---------↵
    -0.06
    .memory
    -0.06
    orneys
    -0.06
    σμού
    -0.06
    _SYM
    -0.06
    aju
    -0.06
    notifications
    -0.06
    POSITIVE LOGITS
     oats
    0.13
     oat
    0.13
     oath
    0.07
    fant
    0.07
    OAD
    0.06
     �
    0.06
    ớt
    0.06
     JAVA
    0.06
     Quân
    0.06
    #SBATCH
    0.06
    Act Density 0.001%

    No Known Activations