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

    Neuronpedia

    INDEX
    Explanations

    host or hosted something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ších
    0.71
    ா
    0.67
    ᱐
    0.59
    ো
    0.57
     expediente
    0.57
    }}^{\
    0.56
    اية
    0.56
    ى
    0.56
    0.56
    નુ
    0.55
    POSITIVE LOGITS
     host
    1.03
     hostess
    1.02
     HOST
    0.98
     होस्ट
    0.98
     Host
    0.96
     hosts
    0.90
    Host
    0.87
     hosting
    0.86
     Hosts
    0.85
     Hosted
    0.82
    Act Density 0.014%

    No Known Activations