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

    Neuronpedia

    INDEX
    Explanations

    shared fryers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acol
    0.47
    emen
    0.44
     grossesse
    0.42
    ament
    0.42
    iscal
    0.41
    ophor
    0.40
    ally
    0.40
     pregnancy
    0.39
    imiz
    0.39
    当初
    0.39
    POSITIVE LOGITS
     Poké
    0.51
     Scooter
    0.49
     Bokeh
    0.48
    Bokeh
    0.45
     Retriever
    0.44
    桿
    0.44
     Gson
    0.44
    EXCLUSIVE
    0.43
     Disbursement
    0.42
     CFRP
    0.41
    Act Density 0.000%

    No Known Activations