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

    Neuronpedia

    INDEX
    Explanations

    cases/instances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manifold
    -0.07
    groupName
    -0.06
     rollout
    -0.06
    .Now
    -0.06
     subset
    -0.06
     sw
    -0.06
    	if
    -0.06
    	So
    -0.06
     thing
    -0.06
     rethink
    -0.06
    POSITIVE LOGITS
     अपर
    0.07
    .userData
    0.06
    ुबह
    0.06
     Bakan
    0.06
     frais
    0.06
    ]")
    0.06
     GDPR
    0.06
    .viewModel
    0.06
    _frag
    0.06
     влади
    0.06
    Act Density 0.025%

    No Known Activations