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

    Neuronpedia

    INDEX
    Explanations

    News events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sink
    -0.31
     sinks
    -0.28
     flown
    -0.27
    dest
    -0.26
    -overlay
    -0.25
    Sink
    -0.25
    ?action
    -0.25
     lud
    -0.25
    ë
    -0.25
     Dest
    -0.25
    POSITIVE LOGITS
    rai
    0.28
    inel
    0.28
    éĤ£ä¸Ģ
    0.27
    ieri
    0.27
    å¾·æĭī
    0.26
    è§Ħ
    0.26
    éĻIJ
    0.26
    era
    0.26
    dera
    0.25
    Depart
    0.25
    Act Density 0.029%

    No Known Activations