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

    Neuronpedia

    INDEX
    Explanations

    Palo

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ρ
    -0.07
    ç
    -0.06
    _lens
    -0.06
     people
    -0.06
     περιοχή
    -0.06
    �
    -0.06
    -0.06
    ований
    -0.06
    食べ
    -0.06
     τον
    -0.06
    POSITIVE LOGITS
     Dante
    0.07
    Contin
    0.07
     Concat
    0.07
     Next
    0.06
     emph
    0.06
     زمان
    0.06
    ','=
    0.06
    (Attribute
    0.06
    acl
    0.06
     MyBase
    0.06
    Act Density 0.001%

    No Known Activations