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

    Neuronpedia

    INDEX
    Explanations

    server

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     confess
    -0.07
     cleaning
    -0.06
     Cleaning
    -0.06
     painting
    -0.06
    -part
    -0.06
     blend
    -0.06
     breaks
    -0.06
     preserves
    -0.06
    _CLOSE
    -0.06
    endas
    -0.06
    POSITIVE LOGITS
    ])):↵
    0.07
     satire
    0.07
    lardı
    0.07
    ční
    0.06
    �
    0.06
    VertexAttrib
    0.06
    (il
    0.06
     (#
    0.06
    -through
    0.06
    建设
    0.06
    Act Density 0.010%

    No Known Activations