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

    Neuronpedia

    INDEX
    Explanations

    GDPR, authentication, validation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subnet
    0.45
    敤
    0.44
    uminescence
    0.43
     cipher
    0.42
    вач
    0.42
     కుమార్
    0.42
    がありますが
    0.42
    書法
    0.42
    槤
    0.42
     hemodynamic
    0.42
    POSITIVE LOGITS
    X
    0.56
    en
    0.54
    ce
    0.54
    ad
    0.52
    M
    0.52
    is
    0.50
    cantidad
    0.50
    ;
    0.48
    ة
    0.48
    se
    0.46
    Act Density 0.129%

    No Known Activations