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

    Neuronpedia

    INDEX
    Explanations

    radiation shielding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    время
    0.42
     hostname
    0.41
    dimensions
    0.40
    hostname
    0.39
    Hostname
    0.39
    time
    0.38
    potato
    0.38
    ândia
    0.38
    體的
    0.37
    ayla
    0.37
    POSITIVE LOGITS
     impulses
    0.41
     impulsive
    0.41
     impulse
    0.40
     LH
    0.40
     flirt
    0.39
     RT
    0.39
     vektor
    0.38
     बह
    0.38
     vl
    0.38
     froth
    0.38
    Act Density 0.000%

    No Known Activations