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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ũng
    -0.07
     palp
    -0.06
    _fds
    -0.06
    iore
    -0.06
    .published
    -0.06
     مرکز
    -0.06
    おり
    -0.06
     innocent
    -0.06
    ування
    -0.06
    ιστο
    -0.06
    POSITIVE LOGITS
    ��
    0.07
    NEY
    0.07
     Hammer
    0.07
    _FIN
    0.06
    _DF
    0.06
     Committee
    0.06
    รม
    0.06
     Spider
    0.06
     gelenek
    0.06
     mong
    0.06
    Act Density 0.044%

    No Known Activations