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

    Neuronpedia

    INDEX
    Explanations

    words related to crime scenes and death

    oai_token-act-pair · gemini-2.0-flash

    blood

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Drapeau
    -0.51
    domada
    -0.51
    setupUi
    -0.51
    FixedSize
    -0.50
    لينكات
    -0.49
     keynote
    -0.47
    hdysval
    -0.47
    capsulation
    -0.47
    Ligne
    -0.47
    <bos>
    -0.47
    POSITIVE LOGITS
     blood
    1.21
     mud
    1.12
    blood
    1.05
     BLOOD
    0.99
     muddy
    0.93
    mud
    0.92
     Blood
    0.91
    Blood
    0.91
    血
    0.90
     Mud
    0.89
    Act Density 1.279%

    No Known Activations