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

    Neuronpedia

    INDEX
    Explanations

    legitimate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    partement
    -0.08
     progett
    -0.08
     temat
    -0.07
     rischio
    -0.07
     lento
    -0.07
    概要
    -0.07
     нест
    -0.07
     ridd
    -0.07
     Nested
    -0.07
     Manuals
    -0.07
    POSITIVE LOGITS
     lawful
    0.10
     ilíc
    0.08
     sinister
    0.08
    -ar
    0.08
    依法
    0.08
     comply
    0.08
     legally
    0.08
     संघर्ष
    0.07
     arth
    0.07
    Conflict
    0.07
    Act Density 0.004%

    No Known Activations