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

    Neuronpedia

    INDEX
    Explanations

    basic needs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /client
    -0.08
    _TARGET
    -0.08
    対象
    -0.08
    target
    -0.08
    acct
    -0.08
     tangent
    -0.07
     flags
    -0.07
     účet
    -0.07
    /front
    -0.07
     평
    -0.07
    POSITIVE LOGITS
     bathrooms
    0.10
     bathroom
    0.10
     Bathroom
    0.10
     necessidades
    0.10
     restroom
    0.10
     ഭക്ഷ
    0.09
     thirsty
    0.09
     hungry
    0.09
     sintomas
    0.09
    供应
    0.09
    Act Density 0.041%

    No Known Activations