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

    Neuronpedia

    INDEX
    Explanations

    modal verbs and requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     polymorphisms
    0.49
     sealer
    0.48
     stipend
    0.46
     depletion
    0.46
     condenser
    0.46
     ။
    0.46
     stejně
    0.46
     cosi
    0.46
    讷
    0.46
     singlet
    0.45
    POSITIVE LOGITS
    g
    0.49
    c
    0.46
    も
    0.45
    b
    0.44
    jade
    0.44
     inconven
    0.43
    不容易
    0.43
     inconvenient
    0.43
    oh
    0.42
    т
    0.42
    Act Density 0.002%

    No Known Activations