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

    Neuronpedia

    INDEX
    Explanations

    technical enumeration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     episodic
    0.44
     abducted
    0.42
     whose
    0.38
     transgenic
    0.38
     antipsych
    0.37
     the
    0.37
     expressed
    0.36
     pertinent
    0.36
     abst
    0.35
     criticized
    0.35
    POSITIVE LOGITS
    或其他
    0.43
    +
    0.42
    /"
    0.41
    ুরে
    0.41
    ،
    0.40
     وغيرها
    0.39
    之类的
    0.38
     वगैरह
    0.37
    си
    0.37
     چی
    0.37
    Act Density 0.061%

    No Known Activations