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

    Neuronpedia

    INDEX
    Explanations

    details about humanoid robots and their functionalities.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    introducing concepts or examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     logró
    0.27
     شاہ
    0.26
     című
    0.26
     وأ
    0.26
     diox
    0.25
    ammlung
    0.25
     وم
    0.25
     والم
    0.25
     surgiu
    0.24
     uranium
    0.24
    POSITIVE LOGITS
     it
    0.44
     это
    0.43
     यह
    0.41
     It
    0.41
    Это
    0.40
     זה
    0.40
    это
    0.38
    It
    0.36
     এটা
    0.34
    これは
    0.34
    Act Density 0.619%

    No Known Activations