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

    Neuronpedia

    INDEX
    Explanations

    Fisherman's Wharf

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Naturally
    0.41
     Needless
    0.38
     biologiques
    0.36
     Edit
    0.36
     prefs
    0.36
    দর্শক
    0.36
    umination
    0.36
    غط
    0.35
    Edit
    0.35
     Sync
    0.35
    POSITIVE LOGITS
     Zh
    0.44
    读
    0.42
    钣
    0.42
     utilizando
    0.42
     വായി
    0.41
     narrated
    0.40
     Zhi
    0.40
     stade
    0.39
     সাহায্যের
    0.39
    책
    0.39
    Act Density 0.001%

    No Known Activations