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

    Neuronpedia

    INDEX
    Explanations

    medical treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sentencing
    -0.07
     zaman
    -0.07
    aller
    -0.06
    atisfied
    -0.06
     arthritis
    -0.06
     Anne
    -0.06
    ció
    -0.06
    Xml
    -0.06
    adlo
    -0.06
    ових
    -0.06
    POSITIVE LOGITS
    loon
    0.07
     MIL
    0.07
     got
    0.07
     избав
    0.07
     Warning
    0.07
    ुव
    0.06
    �
    0.06
    .Never
    0.06
     TEM
    0.06
    aight
    0.06
    Act Density 0.060%

    No Known Activations