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

    Neuronpedia

    INDEX
    Explanations

    specific

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	git
    -0.07
    まだ
    -0.07
     використання
    -0.06
    ivic
    -0.06
    _security
    -0.06
     assurances
    -0.06
     Hir
    -0.06
    над
    -0.06
     mulheres
    -0.06
    τας
    -0.06
    POSITIVE LOGITS
    .GenerationType
    0.07
     own
    0.07
     ghosts
    0.07
    ],"
    0.07
     meets
    0.07
     Own
    0.06
    .engine
    0.06
     ATS
    0.06
    .once
    0.06
    oolStrip
    0.06
    Act Density 0.011%

    No Known Activations