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

    Neuronpedia

    INDEX
    Explanations

    Code with translations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ........
    -0.08
     organism
    -0.07
    \">
    -0.06
    _$
    -0.06
    	String
    -0.06
    '<
    -0.06
    HashMap
    -0.06
    //-
    -0.06
    하지만
    -0.06
    --------
    -0.06
    POSITIVE LOGITS
     trespass
    0.06
    ованих
    0.06
     Tenant
    0.06
    採
    0.06
     εγκα
    0.06
    uid
    0.06
    ального
    0.06
     Ellis
    0.06
     가입
    0.06
     нескольких
    0.06
    Act Density 0.003%

    No Known Activations