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

    Neuronpedia

    INDEX
    Explanations

    conversations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    َال
    -0.07
     Wrong
    -0.07
     nale
    -0.07
     //↵↵
    -0.07
    �
    -0.07
     INFORMATION
    -0.07
     Shell
    -0.06
    ruptions
    -0.06
    獨
    -0.06
    واء
    -0.06
    POSITIVE LOGITS
     ELF
    0.06
     расч
    0.06
    _HEIGHT
    0.06
    чук
    0.06
    PFN
    0.06
    traits
    0.05
    (Color
    0.05
    edelta
    0.05
     implication
    0.05
    .owl
    0.05
    Act Density 0.206%

    No Known Activations