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

    Neuronpedia

    INDEX
    Explanations

    Medical diagnoses/treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     formatting
    -0.08
    quisitions
    -0.07
    _translation
    -0.07
     passengers
    -0.07
     díky
    -0.07
     şekilde
    -0.07
    	dp
    -0.07
    erp
    -0.06
     materials
    -0.06
    &p
    -0.06
    POSITIVE LOGITS
     THESE
    0.07
    lassen
    0.07
    ượu
    0.06
    ******↵↵
    0.06
     Kaw
    0.06
    ILogger
    0.06
     swingerclub
    0.06
     توم
    0.06
    .Option
    0.06
    rew
    0.06
    Act Density 0.046%

    No Known Activations