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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     safari
    -0.07
    ד
    -0.07
     Acad
    -0.06
    belum
    -0.06
     tactic
    -0.06
     yours
    -0.06
    -primary
    -0.06
    _repo
    -0.06
    .Day
    -0.06
    hower
    -0.06
    POSITIVE LOGITS
    ’↵↵
    0.07
    �
    0.06
    [js
    0.06
     Netz
    0.06
    	constexpr
    0.06
     hinter
    0.06
    electron
    0.06
     Vid
    0.06
     �
    0.06
    Throughout
    0.06
    Act Density 0.041%

    No Known Activations