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

    Neuronpedia

    INDEX
    Explanations

    predicting the next word

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    琕
    0.38
     смысле
    0.37
     बनाने
    0.37
     ബെ
    0.37
     Excluding
    0.37
     mū
    0.36
    Mutex
    0.36
     estren
    0.35
     верну
    0.35
     paralyzed
    0.35
    POSITIVE LOGITS
     proliferation
    0.39
     representation
    0.38
     sympathetic
    0.37
     SSB
    0.37
    SBP
    0.37
     Representation
    0.36
     ig
    0.36
     kind
    0.35
    irties
    0.34
    floating
    0.34
    Act Density 0.005%

    No Known Activations